diff --git a/tools/ui/src/lib/components/app/models/discover/DownloadProgressBar.svelte b/tools/ui/src/lib/components/app/models/discover/DownloadProgressBar.svelte
deleted file mode 100644
index 6f4973c12e..0000000000
--- a/tools/ui/src/lib/components/app/models/discover/DownloadProgressBar.svelte
+++ /dev/null
@@ -1,32 +0,0 @@
-<script lang="ts">
-	interface Props {
-		downloadedBytes: number;
-		totalBytes: number;
-		overlay?: boolean;
-	}
-
-	let { downloadedBytes, overlay = false, totalBytes }: Props = $props();
-
-	let fraction = $derived.by(() => {
-		if (totalBytes <= 0) return 0;
-
-		return Math.min(Math.max(downloadedBytes / totalBytes, 0), 1);
-	});
-	let percent = $derived(Math.round(fraction * 100));
-</script>
-
-{#if overlay}
-	<div class="pointer-events-none absolute inset-x-0 bottom-0 h-0.5 overflow-hidden rounded-b-sm">
-		<div
-			class="h-full bg-primary transition-[width] duration-200 ease-out"
-			style="width: {percent}%"
-		></div>
-	</div>
-{:else}
-	<div class="h-1 w-full overflow-hidden rounded-full bg-muted">
-		<div
-			class="h-full bg-primary transition-[width] duration-200 ease-out"
-			style="width: {percent}%"
-		></div>
-	</div>
-{/if}
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscover.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscover.svelte
new file mode 100644
index 0000000000..01b4e90e0a
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscover.svelte
@@ -0,0 +1,138 @@
+<script lang="ts">
+	import {
+		ModelsDiscoverDetails,
+		ModelsDiscoverList,
+		ModelsDiscoverListSearch
+	} from '$lib/components/app/models/discover';
+	import { Button } from '$lib/components/ui/button';
+	import { HuggingFaceService } from '$lib/services';
+	import { modelsDiscoverStore } from '$lib/stores';
+	import type { HfModelDetailInfo, HfModelSibling } from '$lib/types';
+
+	let selectedId = $state<string | null>(null);
+	let searchQuery = $state('');
+	let searchTimeout: ReturnType<typeof setTimeout> | null = null;
+
+	// Detail pane state, reloaded when the selection changes.
+	let details = $state<HfModelDetailInfo | null>(null);
+	let files = $state<HfModelSibling[]>([]);
+	let readme = $state<string | null>(null);
+	let detailLoading = $state(false);
+	let detailError = $state<string | null>(null);
+
+	// Load the sidebar list on mount (the component is mounted when the dialog opens).
+	$effect(() => {
+		void modelsDiscoverStore.fetch();
+		void modelsDiscoverStore.search('');
+	});
+
+	// Auto-select the first model.
+	$effect(() => {
+		const first = modelsDiscoverStore.firstModel;
+
+		if (!selectedId && first) {
+			selectedId = first.id;
+		}
+	});
+
+	function handleSearchInput(value: string) {
+		searchQuery = value;
+
+		if (searchTimeout) clearTimeout(searchTimeout);
+
+		searchTimeout = setTimeout(() => {
+			void modelsDiscoverStore.search(value);
+		}, 300);
+	}
+
+	// Load the detail pane for the selected model (component is reused across
+	// selections, so this re-fetches on every change).
+	$effect(() => {
+		const id = selectedId;
+
+		if (!id) return;
+
+		let cancelled = false;
+
+		detailLoading = true;
+		detailError = null;
+
+		void (async () => {
+			try {
+				const [info, tree, readmeText] = await Promise.all([
+					HuggingFaceService.getDetails(id),
+					HuggingFaceService.getTree(id),
+					HuggingFaceService.getReadme(id)
+				]);
+
+				if (cancelled) return;
+
+				if (!info) {
+					detailError = 'Model not found';
+
+					return;
+				}
+
+				details = info;
+				files = HuggingFaceService.filterByExtension(
+					HuggingFaceService.collapseGgufShards(tree),
+					'.gguf'
+				);
+				readme = readmeText;
+			} catch (err) {
+				if (cancelled) return;
+
+				detailError = err instanceof Error ? err.message : 'Failed to load model';
+			} finally {
+				if (!cancelled) detailLoading = false;
+			}
+		})();
+
+		return () => {
+			cancelled = true;
+		};
+	});
+</script>
+
+<aside
+	class="w-md shrink-0 self-start border-r border-border/40 bg-background overflow-y-auto md:pr-4 h-full space-y-4"
+>
+	<ModelsDiscoverListSearch bind:value={searchQuery} onSearch={handleSearchInput} />
+
+	<!-- One list instance, so the rows keep their state across search round trips;
+		 skeleton rows replace them while the initial catalog or a query loads. -->
+	<div>
+		{#if modelsDiscoverStore.error}
+			<div class="flex flex-col items-start gap-2 p-4">
+				<p class="text-sm text-destructive">{modelsDiscoverStore.error}</p>
+
+				<Button onclick={() => void modelsDiscoverStore.fetch()} size="sm" variant="outline">
+					Retry
+				</Button>
+			</div>
+		{:else if !modelsDiscoverStore.loading && !modelsDiscoverStore.searching && modelsDiscoverStore.models.length === 0}
+			<p class="p-4 text-sm text-muted-foreground">No models found</p>
+		{:else}
+			<ModelsDiscoverList
+				activeId={selectedId}
+				loading={modelsDiscoverStore.loading || modelsDiscoverStore.searching}
+				models={modelsDiscoverStore.models}
+				onSelect={(id) => (selectedId = id)}
+				showBaseModelAvatar
+			/>
+		{/if}
+	</div>
+</aside>
+
+<main class="overflow-y-auto">
+	{#if selectedId}
+		<ModelsDiscoverDetails
+			{details}
+			error={detailError}
+			{files}
+			loading={detailLoading}
+			modelId={selectedId}
+			{readme}
+		/>
+	{/if}
+</main>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverChatTemplateDialog.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverChatTemplateDialog.svelte
new file mode 100644
index 0000000000..45eb209a2a
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverChatTemplateDialog.svelte
@@ -0,0 +1,67 @@
+<script lang="ts">
+	import { Check, Copy, X } from '@lucide/svelte';
+	import * as Dialog from '$lib/components/ui/dialog';
+	import { copyToClipboard } from '$lib/utils';
+
+	interface Props {
+		open?: boolean;
+		chatTemplate: string;
+		onOpenChange?: (open: boolean) => void;
+	}
+
+	let { chatTemplate, onOpenChange, open = $bindable(false) }: Props = $props();
+
+	function handleOpenChange(value: boolean) {
+		open = value;
+		onOpenChange?.(value);
+	}
+
+	let copied = $state(false);
+
+	async function copy() {
+		await copyToClipboard(chatTemplate);
+		copied = true;
+		setTimeout(() => (copied = false), 1500);
+	}
+</script>
+
+<Dialog.Root onOpenChange={handleOpenChange} {open}>
+	<Dialog.Content
+		class="flex max-h-[calc(100vh-4rem)] flex-col gap-0 p-0 md:w-[calc(100vw-4rem)]! md:max-w-4xl!"
+	>
+		<!-- The header's corner-pinned close X never lines up with a padded flex row,
+		     so it is replaced by one inside the row, aligned with the title -->
+		<Dialog.Header
+			class="flex-row items-center gap-2 border-b border-border/40 p-4"
+			showCloseButton={false}
+		>
+			<Dialog.Title class="text-sm font-semibold">Chat template</Dialog.Title>
+
+			<button
+				aria-label="Copy chat template"
+				class="inline-flex cursor-pointer items-center gap-1.5 rounded-md border border-border/30 px-2 py-1 text-xs font-medium shadow-sm transition-colors hover:bg-muted dark:border-border/20"
+				onclick={() => void copy()}
+				type="button"
+			>
+				{#if copied}
+					<Check class="h-3.5 w-3.5 text-green-500" />
+				{:else}
+					<Copy class="h-3.5 w-3.5" />
+				{/if}
+
+				Copy
+			</button>
+
+			<Dialog.Close
+				aria-label="Close"
+				class="ml-auto inline-flex cursor-pointer items-center justify-center rounded-md p-1.5 text-muted-foreground/70 transition-colors hover:bg-muted-foreground/10 hover:text-foreground"
+				type="button"
+			>
+				<X class="h-4 w-4" />
+			</Dialog.Close>
+		</Dialog.Header>
+
+		<pre
+			class="flex-1 overflow-auto p-4 font-mono text-xs break-all whitespace-pre-wrap text-muted-foreground">{chatTemplate}</pre>
+	</Dialog.Content>
+</Dialog.Root>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetails.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetails.svelte
new file mode 100644
index 0000000000..cecdda738c
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetails.svelte
@@ -0,0 +1,96 @@
+<script lang="ts">
+	import { ModelsDiscoverDetailsDownloadOptions } from './ModelsDiscoverDetailsDownloadOptions';
+	import ModelsDiscoverDetailsHeader from './ModelsDiscoverDetailsHeader.svelte';
+	import ModelsDiscoverDetailsReadme from './ModelsDiscoverDetailsReadme.svelte';
+	import ModelsDiscoverDetailsSkeleton from './ModelsDiscoverDetailsSkeleton.svelte';
+	import { OTHER_BIT_DEPTH } from '$lib/constants';
+	import { ModelAuxSidecar } from '$lib/enums';
+	import { HuggingFaceService } from '$lib/services';
+	import type { HfModelDetailInfo, HfModelSibling, ModelBitDepthRow } from '$lib/types';
+	import { detectThinkingSupport, detectToolUseSupport } from '$lib/utils';
+	import { SvelteMap } from 'svelte/reactivity';
+
+	interface Props {
+		/** Full HuggingFace model id, e.g. `ggml-org/gemma-3-4b-it-GGUF`. */
+		modelId: string;
+		/** Model details from `/api/models/{id}?full=true`; null while loading. */
+		details: HfModelDetailInfo | null;
+		/** GGUF files of the repo, shards collapsed, sorted by size desc. */
+		files: HfModelSibling[];
+		/** README.md content, frontmatter stripped; null when unavailable. */
+		readme: string | null;
+		/** True while the model data is being fetched. */
+		loading?: boolean;
+		/** Error message when loading failed. */
+		error?: string | null;
+	}
+
+	let { details, error = null, files, loading = false, modelId, readme }: Props = $props();
+
+	let gguf = $derived(details?.gguf);
+	let baseModels = $derived(HuggingFaceService.getBaseModels(details));
+	let licenseTag = $derived.by(() => {
+		const tags = details?.tags ?? [];
+
+		return tags.find((t) => t.startsWith('license:'))?.replace('license:', '') ?? null;
+	});
+
+	// Capabilities derived from HF metadata. Vision comes from an mmproj sidecar
+	// or a multimodal pipeline tag; tool use / reasoning from the chat template.
+	let hasMmproj = $derived(
+		files.some(
+			(f) => HuggingFaceService.extractQuantMeta(f.path)?.sidecar === ModelAuxSidecar.MMPROJ
+		)
+	);
+	let hasVision = $derived(hasMmproj || details?.pipeline_tag === 'image-text-to-text');
+	let hasTools = $derived(detectToolUseSupport(gguf?.chat_template ?? ''));
+	let hasReasoning = $derived(detectThinkingSupport(gguf?.chat_template ?? ''));
+
+	let bitDepthRows = $derived.by<ModelBitDepthRow[]>(() => {
+		const rows = new SvelteMap<number, HfModelSibling[]>();
+
+		for (const file of files) {
+			const meta = HuggingFaceService.extractQuantMeta(file.path);
+
+			// mmproj sidecars are already conveyed by the Vision capability badge;
+			// imatrix ships as a normal chip with its own badge.
+			if (meta?.sidecar === ModelAuxSidecar.MMPROJ) continue;
+
+			const depth = meta?.quant ? HuggingFaceService.getBitDepth(meta.quant) : null;
+			const bucket = depth ?? OTHER_BIT_DEPTH;
+			const list = rows.get(bucket) ?? [];
+
+			list.push(file);
+			rows.set(bucket, list);
+		}
+
+		return Array.from(rows.entries())
+			.map(([bitDepth, rowFiles]) => ({ bitDepth, files: rowFiles }))
+			.sort((a, b) => a.bitDepth - b.bitDepth);
+	});
+</script>
+
+{#if loading}
+	<ModelsDiscoverDetailsSkeleton />
+{:else if error}
+	<div class="flex h-full items-center justify-center py-20">
+		<p class="text-sm text-destructive">{error}</p>
+	</div>
+{:else if details}
+	<div class="space-y-6 p-6 pr-0">
+		<ModelsDiscoverDetailsHeader
+			{baseModels}
+			{details}
+			{gguf}
+			{hasReasoning}
+			{hasTools}
+			{hasVision}
+			{licenseTag}
+			{modelId}
+		/>
+
+		<ModelsDiscoverDetailsDownloadOptions {bitDepthRows} {modelId} />
+
+		<ModelsDiscoverDetailsReadme {readme} />
+	</div>
+{/if}
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptions.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptions.svelte
new file mode 100644
index 0000000000..75ecef320e
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptions.svelte
@@ -0,0 +1,173 @@
+<script lang="ts">
+	import { classify, labelFor } from './download-options.utils';
+	import ModelsDiscoverDetailsDownloadOptionsDownloadCommand from './ModelsDiscoverDetailsDownloadOptionsDownloadCommand.svelte';
+	import ModelsDiscoverDetailsDownloadOptionsRow from './ModelsDiscoverDetailsDownloadOptionsRow.svelte';
+	import { DialogConfirmDownload } from '$lib/components/app/dialogs';
+	import { ModelDownloadConfirmAction, ModelSelectableFileKind } from '$lib/enums';
+	import { HuggingFaceService, ModelsService } from '$lib/services';
+	import { modelsStore } from '$lib/stores';
+	import type {
+		ModelBitDepthRow,
+		ModelDownloadEntryState,
+		ModelQuantOption,
+		ModelSelectableFile
+	} from '$lib/types';
+
+	interface Props {
+		/** Full HuggingFace repo id, e.g. `ggml-org/gemma-3-4b-it-GGUF`. */
+		modelId: string;
+		/** GGUF files grouped by bit depth. */
+		bitDepthRows: ModelBitDepthRow[];
+		/** Download state lookup; defaults to the models store status feed. */
+		getDownloadState?: (
+			repoWithTag: string,
+			filePath: string,
+			isSidecar: boolean
+		) => ModelDownloadEntryState;
+	}
+
+	let { bitDepthRows, getDownloadState, modelId }: Props = $props();
+
+	// Destructive chip actions (delete a downloaded model, cancel a download) are
+	// confirmed here rather than inside each chip: a single shared dialog owned by
+	// the options panel, keyed by the repo+tag the user acted on, so one dialog is
+	// mounted for the whole panel instead of one per chip.
+	// The acted-on target is kept after closing so the copy stays rendered through
+	// the dialog's close transition.
+	let pending: { action: ModelDownloadConfirmAction; repoWithTag: string } = $state({
+		action: ModelDownloadConfirmAction.CANCEL,
+		repoWithTag: ''
+	});
+	let confirmOpen = $state(false);
+
+	function requestCancel(repoWithTag: string) {
+		pending = { action: ModelDownloadConfirmAction.CANCEL, repoWithTag };
+		confirmOpen = true;
+	}
+
+	function requestDelete(repoWithTag: string) {
+		pending = { action: ModelDownloadConfirmAction.DELETE, repoWithTag };
+		confirmOpen = true;
+	}
+
+	function stateFor(
+		repoWithTag: string,
+		filePath: string,
+		isSidecar: boolean
+	): ModelDownloadEntryState {
+		if (getDownloadState) return getDownloadState(repoWithTag, filePath, isSidecar);
+
+		const isDownloading = modelsStore.status.isDownloadInProgress(repoWithTag);
+		const isPaused = modelsStore.status.isDownloadPaused(repoWithTag);
+
+		return {
+			// solo downloads register in /v1/models under the tag (args stay empty),
+			// while drafts pulled by a loaded model only show up as its --model-draft
+			isDownloaded:
+				!isDownloading &&
+				(modelsStore.status.isModelDownloaded(repoWithTag) ||
+					(isSidecar && modelsStore.status.isSidecarDownloaded(modelId, filePath))),
+			isDownloading,
+			isFailed: modelsStore.status.hasFailedDownload(repoWithTag),
+			isPaused,
+			// live progress while downloading, else the frozen snapshot of the pause
+			progress:
+				modelsStore.status.getDownloadProgress(repoWithTag) ??
+				modelsStore.status.getPausedDownloadProgress(repoWithTag),
+			repoWithTag
+		};
+	}
+
+	/**
+	 * Every selectable file with its kind and download state, in row order.
+	 * Single source of truth for the chip rows and the command selects.
+	 */
+	let selectableFiles = $derived.by(() => {
+		const files: (ModelSelectableFile & { state: ModelDownloadEntryState })[] = [];
+
+		for (const row of bitDepthRows) {
+			for (const file of row.files) {
+				const meta = HuggingFaceService.extractQuantMeta(file.path);
+				const tag = ModelsService.buildDownloadTag(
+					modelId,
+					meta?.quant ?? null,
+					meta?.sidecar ?? null
+				);
+
+				files.push({
+					...file,
+					kind: classify(file.path),
+					state: stateFor(tag, file.path, Boolean(meta?.sidecar))
+				});
+			}
+		}
+
+		return files;
+	});
+
+	/** Rows for the row component: per-bit-depth files with state attached. */
+	let rows = $derived.by(() =>
+		bitDepthRows.map((row) => {
+			const paths = new Set(row.files.map((f) => f.path));
+
+			return {
+				bitDepth: row.bitDepth,
+				files: selectableFiles.filter((f) => paths.has(f.path))
+			};
+		})
+	);
+
+	function optionFor(file: ModelSelectableFile): ModelQuantOption {
+		return {
+			label: labelFor(file.path),
+			path: file.path
+		};
+	}
+
+	/** Non-draft quants for the command's base select, in row order. */
+	let mainOptions = $derived(
+		selectableFiles.filter((f) => f.kind === ModelSelectableFileKind.MAIN).map(optionFor)
+	);
+
+	/**
+	 * Draft options for the command's draft select, with their sidecar type
+	 * (MTP, DFLASH...) since a repo can ship more than one draft flavour.
+	 */
+	let draftOptions = $derived(
+		selectableFiles
+			.filter((f) => f.kind === ModelSelectableFileKind.DRAFT)
+			.map((f) => ({
+				...optionFor(f),
+				badge: HuggingFaceService.extractQuantMeta(f.path)?.sidecar ?? null
+			}))
+	);
+</script>
+
+{#if bitDepthRows.length}
+	<section class="rounded-3xl border border-border/30 bg-muted/60 shadow-sm dark:border-border/20">
+		<!-- One chip per file, each an independent download action with its own
+			 lifecycle state; nothing here selects anything. -->
+		<div class="flex w-full flex-col divide-y divide-border/50 px-4 pb-1 dark:divide-border/35">
+			{#each rows as row (row.bitDepth)}
+				<ModelsDiscoverDetailsDownloadOptionsRow
+					bitDepth={row.bitDepth}
+					files={row.files}
+					onRequestCancel={requestCancel}
+					onRequestDelete={requestDelete}
+				/>
+			{/each}
+		</div>
+
+		<!-- Terminal command preview, standalone: its picks are not bound to the chips. -->
+		<div class="border-t border-border/50 px-4 pt-3.5 pb-4 dark:border-border/35">
+			<ModelsDiscoverDetailsDownloadOptionsDownloadCommand {draftOptions} {mainOptions} {modelId} />
+		</div>
+	</section>
+{/if}
+
+<DialogConfirmDownload
+	action={pending.action}
+	onClose={() => (confirmOpen = false)}
+	open={confirmOpen}
+	repoWithTag={pending.repoWithTag}
+/>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsDownloadCommand.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsDownloadCommand.svelte
new file mode 100644
index 0000000000..e380505f38
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsDownloadCommand.svelte
@@ -0,0 +1,278 @@
+<script lang="ts">
+	import { Check, Copy, Plus, X } from '@lucide/svelte';
+	import * as Select from '$lib/components/ui/select';
+	import {
+		DEFAULT_BASE_BIT_DEPTH,
+		MODEL_ID,
+		type ModelSidecar,
+		OTHER_BIT_DEPTH,
+		SERVE_COMMAND,
+		SPEC_TYPE
+	} from '$lib/constants';
+	import { HuggingFaceService } from '$lib/services';
+	import type { ModelQuantOption } from '$lib/types';
+	import { copyToClipboard } from '$lib/utils';
+
+	interface Props {
+		modelId: string;
+		/** Non-draft quants of the repo, in bit-depth row order. */
+		mainOptions: ModelQuantOption[];
+		/** Draft sidecar files with their sidecar badge; empty when the repo ships none. */
+		draftOptions: (ModelQuantOption & { badge: ModelSidecar | null })[];
+	}
+
+	let { draftOptions, mainOptions, modelId }: Props = $props();
+
+	// Command picks, owned here: nothing two-way binds them to the quant chips.
+	let basePick = $state<string | null>(null);
+	let draftPick = $state<string | null>(null);
+	let draftTypePick = $state<ModelSidecar | null>(null);
+	let withDraft = $state(false);
+
+	function bitDepthOf(path: string): number {
+		const quant = HuggingFaceService.extractQuantMeta(path)?.quant;
+
+		return quant ? (HuggingFaceService.getBitDepth(quant) ?? OTHER_BIT_DEPTH) : OTHER_BIT_DEPTH;
+	}
+
+	/**
+	 * Base file the command points at: the user's pick while it still exists in
+	 * the options, else the 4-bit file, else the lowest bit depth available. A
+	 * stale pick (the details pane switched models) falls back on its own.
+	 */
+	let baseOption = $derived.by(() => {
+		const picked = mainOptions.find((option) => option.path === basePick);
+
+		if (picked) return picked;
+
+		const preferred = mainOptions.find(
+			(option) => bitDepthOf(option.path) === DEFAULT_BASE_BIT_DEPTH
+		);
+
+		if (preferred) return preferred;
+
+		const ranked = [...mainOptions].sort((a, b) => bitDepthOf(a.path) - bitDepthOf(b.path));
+
+		return ranked[0] ?? null;
+	});
+
+	/** Draft sidecar types the repo ships, in option order. */
+	let specTypes = $derived(
+		draftOptions
+			.map((option) => option.badge)
+			.filter((badge): badge is ModelSidecar => badge !== null)
+			.filter((badge, index, all) => all.indexOf(badge) === index)
+	);
+
+	/**
+	 * Draft type the --spec-type select points at: the user's pick while it
+	 * still exists, else the first type the repo ships.
+	 */
+	let draftType = $derived(
+		draftTypePick && specTypes.includes(draftTypePick) ? draftTypePick : (specTypes[0] ?? null)
+	);
+
+	/** Draft files of the picked type; the quant select only offers these. */
+	let typeDraftOptions = $derived(draftOptions.filter((option) => option.badge === draftType));
+
+	/** Draft file the -hfd tag points at: the user's pick, else the first of the type. */
+	let draftOption = $derived(
+		withDraft
+			? (typeDraftOptions.find((option) => option.path === draftPick) ??
+					typeDraftOptions[0] ??
+					null)
+			: null
+	);
+
+	/** Quant of the file the `-hf` tag points at; null when the file carries no quant. */
+	let mainQuant = $derived(
+		baseOption ? (HuggingFaceService.extractQuantMeta(baseOption.path)?.quant ?? null) : null
+	);
+
+	/** Quant of the file the `-hfd` tag points at. */
+	let draftQuant = $derived(
+		draftOption ? (HuggingFaceService.extractQuantMeta(draftOption.path)?.quant ?? null) : null
+	);
+
+	/** `--spec-type` value; null when no draft type resolved. */
+	let specType = $derived(draftType ? SPEC_TYPE[draftType] : null);
+
+	/** The llama serve command, composed from the inline picks. */
+	let command = $derived.by(() => {
+		const parts = [
+			SERVE_COMMAND.BIN,
+			SERVE_COMMAND.SUBCOMMAND,
+			SERVE_COMMAND.MODEL_FLAG,
+			mainQuant ? `${modelId}${MODEL_ID.QUANTIZATION_SEPARATOR}${mainQuant}` : modelId
+		];
+
+		if (draftOption && draftQuant) {
+			parts.push(
+				SERVE_COMMAND.DRAFT_FLAG,
+				`${modelId}${MODEL_ID.QUANTIZATION_SEPARATOR}${draftQuant}`,
+				SERVE_COMMAND.SPEC_TYPE_FLAG,
+				specType ?? ''
+			);
+		}
+
+		return parts.join(' ');
+	});
+
+	let copied = $state(false);
+
+	async function copy() {
+		await copyToClipboard(command);
+		copied = true;
+		setTimeout(() => (copied = false), 1500);
+	}
+</script>
+
+<!-- <div aria-hidden="true" class="flex items-center gap-3 mt-2 mb-4">
+	<span class="h-px flex-1 bg-border/50"></span>
+
+	<span class="text-xs whitespace-nowrap text-muted-foreground"> or run in your terminal </span>
+
+	<span class="h-px flex-1 bg-border/50"></span>
+</div> -->
+
+<div
+	class="relative flex items-center gap-2 overflow-hidden rounded-lg border border-border/40 bg-background py-2.5 pl-4 pr-10 shadow-xs dark:border-border/35 dark:bg-background/50"
+>
+	<!-- Single line: long commands scroll horizontally instead of wrapping. -->
+	<div
+		class="flex min-w-0 flex-1 items-center gap-x-2 overflow-x-auto py-0.5 font-mono text-xs whitespace-nowrap text-foreground/90"
+	>
+		<span class="shrink-0">{SERVE_COMMAND.BIN}</span>
+
+		<span class="shrink-0">{SERVE_COMMAND.SUBCOMMAND}</span>
+
+		<span class="shrink-0">{SERVE_COMMAND.MODEL_FLAG}</span>
+
+		<span class="shrink-0">
+			{modelId}{mainQuant ? MODEL_ID.QUANTIZATION_SEPARATOR : ''}
+		</span>
+
+		<!-- Base quant: always part of the command, the 4-bit file by default. -->
+		{#if baseOption}
+			<Select.Root onValueChange={(v) => v && (basePick = v)} type="single" value={baseOption.path}>
+				<Select.Trigger
+					aria-label="Base model quantization"
+					class="-ml-2 border-primary/15 bg-primary/[0.07] font-mono text-foreground hover:bg-primary/15 focus-visible:border-primary/40 focus-visible:ring-0"
+					size="xs"
+				>
+					{baseOption.label}
+				</Select.Trigger>
+
+				<Select.Content class="font-mono text-xs">
+					{#each mainOptions as option (option.path)}
+						<Select.Item class="text-xs" label={option.label} value={option.path}>
+							{option.label}
+						</Select.Item>
+					{/each}
+				</Select.Content>
+			</Select.Root>
+		{/if}
+
+		<!-- Draft add: a tiny dashed affordance right of the base part; gone once added. -->
+		{#if draftOptions.length && !withDraft}
+			<button
+				aria-label="Add draft model"
+				class="mx-1 inline-flex h-5 shrink-0 cursor-pointer items-center gap-1 rounded-md border border-dashed border-border/60 px-1.5 text-[10px] text-muted-foreground transition-colors hover:border-border hover:text-foreground"
+				onclick={() => (withDraft = true)}
+				type="button"
+			>
+				<Plus class="h-3 w-3" />
+
+				add draft model
+			</button>
+		{/if}
+
+		<!-- Draft segment: quant and spec type of the picked draft flavour. The X
+				 at the end drops the whole segment (the add button is gone once added);
+				 it only appears while hovering the segment, or directly on touch -->
+		{#if draftOption}
+			<span class="group/draft inline-flex shrink-0 items-center gap-x-2">
+				<span>{SERVE_COMMAND.DRAFT_FLAG}</span>
+
+				<span class="shrink-0">
+					{modelId}{draftQuant ? MODEL_ID.QUANTIZATION_SEPARATOR : ''}
+				</span>
+
+				<Select.Root
+					onValueChange={(v) => v && (draftPick = v)}
+					type="single"
+					value={draftOption.path}
+				>
+					<Select.Trigger
+						aria-label="Draft model quantization"
+						class="-ml-2 border-primary/15 bg-primary/[0.07] font-mono text-foreground hover:bg-primary/15 focus-visible:border-primary/40 focus-visible:ring-0"
+						size="xs"
+					>
+						{draftOption.label}
+					</Select.Trigger>
+
+					<Select.Content class="font-mono text-xs">
+						{#each typeDraftOptions as option (option.path)}
+							<Select.Item class="text-xs" label={option.label} value={option.path}>
+								{option.label}
+							</Select.Item>
+						{/each}
+					</Select.Content>
+				</Select.Root>
+
+				{#if draftType}
+					<span>{SERVE_COMMAND.SPEC_TYPE_FLAG}</span>
+
+					<!-- the select only earns its chrome when there is a real choice to make -->
+					{#if specTypes.length > 1}
+						<Select.Root
+							onValueChange={(v) => v && (draftTypePick = v as ModelSidecar)}
+							type="single"
+							value={draftType}
+						>
+							<Select.Trigger
+								aria-label="Draft type"
+								class="border-primary/15 bg-primary/[0.07] font-mono text-foreground hover:bg-primary/15 focus-visible:border-primary/40 focus-visible:ring-0"
+								size="xs"
+							>
+								{SPEC_TYPE[draftType]}
+							</Select.Trigger>
+
+							<Select.Content class="font-mono text-xs">
+								{#each specTypes as type (type)}
+									<Select.Item class="text-xs" label={SPEC_TYPE[type]} value={type}>
+										{SPEC_TYPE[type]}
+									</Select.Item>
+								{/each}
+							</Select.Content>
+						</Select.Root>
+					{:else}
+						<span>{SPEC_TYPE[draftType]}</span>
+					{/if}
+				{/if}
+
+				<button
+					aria-label="Remove draft model"
+					class="shrink-0 cursor-pointer text-muted-foreground/60 opacity-0 transition-[opacity,color] duration-150 ease-[cubic-bezier(0.23,1,0.32,1)] hover:text-destructive group-hover/draft:opacity-100 [@media(pointer:coarse)]:opacity-100"
+					onclick={() => (withDraft = false)}
+					type="button"
+				>
+					<X class="h-3 w-3" />
+				</button>
+			</span>
+		{/if}
+	</div>
+
+	<button
+		aria-label="Copy command"
+		class="absolute top-1/2 right-2 -translate-y-1/2 cursor-pointer rounded-md p-1.5 text-muted-foreground/70 transition-colors hover:bg-primary/10 hover:text-foreground"
+		onclick={copy}
+		type="button"
+	>
+		{#if copied}
+			<Check class="h-3.5 w-3.5 text-green-500" />
+		{:else}
+			<Copy class="h-3.5 w-3.5" />
+		{/if}
+	</button>
+</div>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton.svelte
new file mode 100644
index 0000000000..2908ea97a3
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton.svelte
@@ -0,0 +1,244 @@
+<script lang="ts">
+	import ModelsDiscoverDownloadProgressBar from '../../ModelsDiscoverDownloadProgressBar.svelte';
+	import { labelFor } from './download-options.utils';
+	import { Check, Download, Loader2, Pause, Play, RotateCw, X } from '@lucide/svelte';
+	import * as Tooltip from '$lib/components/ui/tooltip';
+	import { HuggingFaceService } from '$lib/services';
+	import { modelsStore } from '$lib/stores';
+	import type { HfModelSibling, ModelDownloadEntryState } from '$lib/types';
+	import type { Snippet } from 'svelte';
+
+	interface Props {
+		/** GGUF file the chip stands for. */
+		file: HfModelSibling;
+		/** Download state of the file, from the parent's status feed. */
+		entry: ModelDownloadEntryState;
+		/**
+		 * Ask the parent to confirm deleting a downloaded model. The chip owns no
+		 * dialog; the parent renders the single confirmation and acts on confirm.
+		 */
+		onRequestDelete?: (repoWithTag: string) => void;
+		/** Ask the parent to confirm cancelling an in-flight download. */
+		onRequestCancel?: (repoWithTag: string) => void;
+	}
+
+	let { entry, file, onRequestCancel, onRequestDelete }: Props = $props();
+
+	// Sidecar kind (mtp, mmproj, ...) tag shown on every chip state; one source so
+	// the idle, in-flight and downloaded variants stay identical.
+	const SIDECAR_BADGE_CLASS =
+		'rounded-md bg-primary px-1 py-0.5 text-[10px] font-semibold tracking-wide text-primary-foreground uppercase';
+
+	/** Queue the download; a failed attempt leaves partial files, drop them first. */
+	async function startDownload() {
+		try {
+			if (entry.isFailed) await modelsStore.status.cancelDownload(entry.repoWithTag);
+
+			await modelsStore.status.downloadModel(entry.repoWithTag);
+		} catch {
+			// the store already toasted the failure
+		}
+	}
+
+	let meta = $derived(HuggingFaceService.extractQuantMeta(file.path));
+	let label = $derived(labelFor(file.path));
+
+	let percent = $derived(
+		entry.progress && entry.progress.totalBytes > 0
+			? Math.round((entry.progress.downloadedBytes / entry.progress.totalBytes) * 100)
+			: null
+	);
+
+	let tooltipText = $derived(
+		entry.isDownloading
+			? 'Pause downloading'
+			: entry.isPaused
+				? 'Resume downloading'
+				: entry.isDownloaded
+					? 'Delete model'
+					: entry.isFailed
+						? `Retry download: ${file.path}`
+						: `Download ${file.path}`
+	);
+</script>
+
+{#snippet chipBody(dividerClass: string)}
+	<!-- badge, label and divider: identical on every chip state -->
+	{#if meta?.sidecar}
+		<span class={SIDECAR_BADGE_CLASS}>
+			{meta.sidecar}
+		</span>
+	{/if}
+
+	<span class="font-medium">{label}</span>
+
+	<span class={dividerClass}></span>
+{/snippet}
+
+<!-- every chip is a tooltip trigger; the button renders as the trigger's child
+     so no nested button element is created -->
+{#snippet tooltipTrigger(tip: string, button: Snippet<[Record<string, unknown>]>)}
+	<Tooltip.Root>
+		<Tooltip.Trigger>
+			{#snippet child({ props })}
+				{@render button(props)}
+			{/snippet}
+		</Tooltip.Trigger>
+
+		<Tooltip.Content>
+			<p>{tip}</p>
+		</Tooltip.Content>
+	</Tooltip.Root>
+{/snippet}
+
+{#snippet deleteChip(props: Record<string, unknown>)}
+	<!-- downloaded chips are delete actions: green check by default, red X on hover -->
+	<button
+		{...props}
+		aria-label={tooltipText}
+		class="group relative inline-flex h-auto cursor-pointer items-center gap-1 rounded-md! border px-2 py-1 text-left font-mono text-xs shadow-sm transition-[background-color,border-color,transform] duration-200 ease-[cubic-bezier(0.23,1,0.32,1)] active:scale-[0.97]
+					border-green-600/25 bg-green-500/5 hover:border-destructive/50 hover:bg-destructive/10 dark:border-green-500/30 dark:bg-green-500/10 dark:hover:border-destructive/50 dark:hover:bg-destructive/15"
+		onclick={() => onRequestDelete?.(entry.repoWithTag)}
+		type="button"
+	>
+		{@render chipBody(
+			'-my-1 mx-0.75 w-px self-stretch bg-green-600/25 transition-colors duration-200 group-hover:bg-destructive/30 dark:bg-green-600/30 dark:group-hover:bg-destructive/30'
+		)}
+
+		<span>{HuggingFaceService.formatFileSize(file.size ?? 0)}</span>
+
+		<!-- icon slot: crossfade check -> x; touch devices show the delete affordance directly -->
+		<span class="relative inline-flex h-3.5 w-3.5 shrink-0 items-center justify-center">
+			<Check
+				class="absolute h-3.5 w-3.5 text-green-500 transition-[opacity,transform] duration-150 ease-[cubic-bezier(0.23,1,0.32,1)] group-hover:scale-75 group-hover:opacity-0 [@media(pointer:coarse)]:hidden"
+			/>
+
+			<X
+				class="absolute h-3.5 w-3.5 scale-75 text-destructive opacity-0 transition-[opacity,transform] duration-150 ease-[cubic-bezier(0.23,1,0.32,1)] group-hover:scale-100 group-hover:opacity-100 [@media(pointer:coarse)]:scale-100 [@media(pointer:coarse)]:opacity-100"
+			/>
+		</span>
+	</button>
+{/snippet}
+
+{#snippet pauseResumeChip(props: Record<string, unknown>)}
+	<button
+		{...props}
+		aria-label={tooltipText}
+		class="flex h-auto min-w-0 flex-1 cursor-pointer items-center gap-1 text-left"
+		onclick={() => {
+			if (entry.isDownloading) void modelsStore.status.pauseDownload(entry.repoWithTag);
+			else void modelsStore.status.downloadModel(entry.repoWithTag).catch(() => {});
+		}}
+		type="button"
+	>
+		{@render chipBody('-my-1 mx-0.75 w-px self-stretch bg-border')}
+
+		{#if percent !== null}
+			<span class="mr-1 tabular-nums">{percent}%</span>
+		{:else if entry.isPaused}
+			<span>Paused</span>
+		{:else}
+			<span>{HuggingFaceService.formatFileSize(file.size ?? 0)}</span>
+		{/if}
+
+		{#if entry.isDownloading}
+			<!-- spinner fades into the pause affordance on hover; opacity only, the
+			     spin keyframes own the transform so scale would fight them -->
+			<span class="relative inline-flex h-3.5 w-3.5 shrink-0 items-center justify-center">
+				<Loader2
+					class="absolute h-3.5 w-3.5 animate-spin text-muted-foreground transition-opacity duration-150 ease-[cubic-bezier(0.23,1,0.32,1)] group-hover:opacity-0 [@media(pointer:coarse)]:hidden"
+				/>
+
+				<Pause
+					class="absolute h-3.5 w-3.5 opacity-0 transition-opacity duration-150 ease-[cubic-bezier(0.23,1,0.32,1)] group-hover:opacity-100 [@media(pointer:coarse)]:opacity-100"
+				/>
+			</span>
+		{:else}
+			<!-- paused: the play affordance fades in on hover; visible directly on touch -->
+			<span class="relative inline-flex h-3.5 w-3.5 shrink-0 items-center justify-center">
+				<Play
+					class="absolute h-3.5 w-3.5 scale-75 opacity-0 transition-[opacity,transform] duration-150 ease-[cubic-bezier(0.23,1,0.32,1)] group-hover:scale-100 group-hover:opacity-100 [@media(pointer:coarse)]:scale-100 [@media(pointer:coarse)]:opacity-100"
+				/>
+			</span>
+		{/if}
+	</button>
+{/snippet}
+
+{#snippet cancelChip(props: Record<string, unknown>)}
+	<!-- cancel slot: same fixed slot and fade as the pause / play affordances
+	     so the two icons line up exactly; the X turns destructive on its hover -->
+	<button
+		{...props}
+		aria-label="Cancel downloading"
+		class="relative grid h-3.5 w-3.5 shrink-0 cursor-pointer items-center justify-center text-muted-foreground/70"
+		onclick={() => onRequestCancel?.(entry.repoWithTag)}
+		type="button"
+	>
+		<X
+			class="h-3.5 w-3.5 transition-[opacity,transform,color] duration-150 ease-[cubic-bezier(0.23,1,0.32,1)] text-destructive [@media(pointer:coarse)]:scale-100 [@media(pointer:coarse)]:opacity-100"
+		/>
+	</button>
+{/snippet}
+
+{#snippet downloadChip(props: Record<string, unknown>)}
+	<!-- idle chips download on click (retry when the last attempt failed) -->
+	<button
+		{...props}
+		aria-label={tooltipText}
+		class="group relative inline-flex h-auto cursor-pointer items-center gap-1 overflow-hidden rounded-md! border px-2 py-1 text-left font-mono text-xs shadow-sm transition-[background-color,border-color,transform] duration-200 ease-[cubic-bezier(0.23,1,0.32,1)] active:scale-[0.97]
+				border-border/30 bg-background hover:bg-muted-foreground/10 dark:border-border/20 dark:bg-muted-foreground/15 dark:text-secondary-foreground dark:hover:bg-muted-foreground/25
+				{entry.isFailed ? 'border-destructive!' : ''}"
+		onclick={() => void startDownload()}
+		type="button"
+	>
+		{#if entry.isFailed}
+			<span
+				class="rounded-md bg-destructive px-1 py-0.5 text-[10px] font-semibold tracking-wide text-destructive-foreground uppercase"
+			>
+				Failed
+			</span>
+		{/if}
+
+		{@render chipBody('-my-1 mx-0.75 w-px self-stretch bg-border')}
+
+		<span>{HuggingFaceService.formatFileSize(file.size ?? 0)}</span>
+
+		<span class="inline-flex h-3.5 w-3.5 shrink-0 items-center justify-center">
+			{#if entry.isFailed}
+				<RotateCw class="h-3.5 w-3.5 text-destructive" />
+			{:else}
+				<Download
+					class="h-3.5 w-3.5 text-muted-foreground transition-colors duration-150 group-hover:text-foreground"
+				/>
+			{/if}
+		</span>
+	</button>
+{/snippet}
+
+{#if entry.isDownloaded}
+	{@render tooltipTrigger(tooltipText, deleteChip)}
+{:else if entry.isDownloading || entry.isPaused}
+	<!-- in-flight / paused chips: the chip body pauses / resumes on click, the X
+	     inside the chip cancels (stops and discards the partial files). The X slot
+	     is reserved, so the chip never reflows when the affordance fades in -->
+	<div
+		class="group relative inline-flex h-auto items-center gap-1 overflow-hidden rounded-md! border px-2 py-1 text-left font-mono text-xs shadow-sm transition-[background-color,border-color,transform] duration-200 ease-[cubic-bezier(0.23,1,0.32,1)] active:scale-[0.97]
+			{entry.isPaused
+			? 'border-yellow-600/40 bg-yellow-500/10 hover:bg-yellow-500/20 dark:border-yellow-500/30 dark:bg-yellow-500/10'
+			: 'border-border/30 bg-background hover:bg-muted-foreground/10 dark:border-border/20 dark:bg-muted-foreground/15'}"
+	>
+		{@render tooltipTrigger(tooltipText, pauseResumeChip)}
+
+		{@render tooltipTrigger('Cancel downloading', cancelChip)}
+
+		{#if percent !== null}
+			<ModelsDiscoverDownloadProgressBar
+				downloadedBytes={entry.progress?.downloadedBytes ?? 0}
+				overlay
+				totalBytes={entry.progress?.totalBytes ?? 0}
+			/>
+		{/if}
+	</div>
+{:else}
+	{@render tooltipTrigger(tooltipText, downloadChip)}
+{/if}
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsRow.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsRow.svelte
new file mode 100644
index 0000000000..11bfe45d42
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/ModelsDiscoverDetailsDownloadOptionsRow.svelte
@@ -0,0 +1,60 @@
+<script lang="ts">
+	import ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton from './ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton.svelte';
+	import {
+		BIT_DEPTH_LABEL_SUFFIX,
+		GIGABYTE_LABEL,
+		OTHER_BIT_DEPTH,
+		OTHER_BIT_DEPTH_LABEL
+	} from '$lib/constants';
+	import { ModelSelectableFileKind } from '$lib/enums';
+	import type { ModelDownloadEntryState, ModelSelectableFile } from '$lib/types';
+	import { minMemoryTierGb } from '$lib/utils';
+
+	interface Props {
+		/** Bit depth of the row; `99` renders as "Other". */
+		bitDepth: number;
+		/** Every GGUF of this bit depth, with download state attached. */
+		files: (ModelSelectableFile & { state: ModelDownloadEntryState })[];
+		/** Forwarded to each chip: ask the parent to confirm a cancel. */
+		onRequestCancel?: (repoWithTag: string) => void;
+		/** Forwarded to each chip: ask the parent to confirm a delete. */
+		onRequestDelete?: (repoWithTag: string) => void;
+	}
+
+	let { bitDepth, files, onRequestCancel, onRequestDelete }: Props = $props();
+
+	let mainFile = $derived(files.find((f) => f.kind === ModelSelectableFileKind.MAIN) ?? null);
+	let draftFile = $derived(files.find((f) => f.kind === ModelSelectableFileKind.DRAFT) ?? null);
+
+	let mainMemGb = $derived(mainFile ? minMemoryTierGb(mainFile.size ?? 0) : null);
+	let draftMemGb = $derived(draftFile ? minMemoryTierGb(draftFile.size ?? 0) : null);
+</script>
+
+<div class="grid grid-cols-[5rem_1fr] items-center gap-3 py-3">
+	<div class="pt-1 text-sm tabular-nums text-muted-foreground">
+		{#if bitDepth === OTHER_BIT_DEPTH}
+			{OTHER_BIT_DEPTH_LABEL}
+		{:else}
+			{bitDepth}{BIT_DEPTH_LABEL_SUFFIX}
+		{/if}
+
+		{#if mainMemGb}
+			<span class="block text-[10px] whitespace-nowrap text-muted-foreground/60">
+				needs at least {mainMemGb}{GIGABYTE_LABEL}{draftMemGb
+					? ` + ${draftMemGb}${GIGABYTE_LABEL}`
+					: ''} memory
+			</span>
+		{/if}
+	</div>
+
+	<div class="flex flex-wrap justify-end gap-1.5">
+		{#each files as file (file.path)}
+			<ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton
+				entry={file.state}
+				{file}
+				{onRequestCancel}
+				{onRequestDelete}
+			/>
+		{/each}
+	</div>
+</div>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/download-options.utils.ts b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/download-options.utils.ts
new file mode 100644
index 0000000000..4dd8accb42
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/download-options.utils.ts
@@ -0,0 +1,28 @@
+import { DRAFT_FILE_LABEL, MODEL_ID, PATH_SEPARATOR } from '$lib/constants';
+import { ModelSelectableFileKind } from '$lib/enums';
+import { HuggingFaceService } from '$lib/services';
+import { isAuxSidecar, isDraftSidecar } from '$lib/utils';
+
+/** Kind of a file path: the main weights, a draft sidecar, or an aux sidecar (mmproj). */
+export function classify(path: string): ModelSelectableFileKind {
+	const sidecar = HuggingFaceService.extractQuantMeta(path)?.sidecar;
+
+	if (!sidecar) return ModelSelectableFileKind.MAIN;
+
+	return isAuxSidecar(sidecar) ? ModelSelectableFileKind.AUX : ModelSelectableFileKind.DRAFT;
+}
+
+/** Display label of a file: its quant, else the file name without the extension. */
+export function labelFor(path: string): string {
+	const meta = HuggingFaceService.extractQuantMeta(path);
+
+	if (meta?.quant) return meta.quant;
+
+	// Quantless sidecar files: the chip badge already carries the sidecar type,
+	// so the label only marks draft files; aux sidecars badge alone.
+	if (meta?.sidecar) return isDraftSidecar(meta.sidecar) ? DRAFT_FILE_LABEL : '';
+
+	const basename = path.split(PATH_SEPARATOR).pop() ?? path;
+
+	return basename.replace(MODEL_ID.WEIGHT_EXTENSION_REGEX, '');
+}
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/index.ts b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/index.ts
new file mode 100644
index 0000000000..b5c0ebef67
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsDownloadOptions/index.ts
@@ -0,0 +1,40 @@
+/**
+ *
+ * MODELS DISCOVER - DETAILS - DOWNLOAD OPTIONS
+ *
+ * The download area of the detail pane: GGUF files grouped by bit depth, each an
+ * independent download action chip, plus the standalone terminal command preview.
+ *
+ */
+
+/**
+ * **ModelsDiscoverDetailsDownloadOptions** - GGUF download options
+ *
+ * Groups GGUF files by bit depth and renders one independent download
+ * action chip per file, plus the standalone terminal command preview.
+ */
+export { default as ModelsDiscoverDetailsDownloadOptions } from './ModelsDiscoverDetailsDownloadOptions.svelte';
+
+/**
+ * **ModelsDiscoverDetailsDownloadOptionsRow** - One bit-depth group of quants
+ *
+ * A single bit-depth row inside ModelsDiscoverDetailsDownloadOptions: the
+ * depth label with its memory hint and the quant chips of that depth.
+ */
+export { default as ModelsDiscoverDetailsDownloadOptionsRow } from './ModelsDiscoverDetailsDownloadOptionsRow.svelte';
+
+/**
+ * **ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton** - One quant chip
+ *
+ * A single GGUF file as an independent action chip: download / retry when
+ * idle, pause / resume / cancel while in flight, delete when downloaded.
+ */
+export { default as ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton } from './ModelsDiscoverDetailsDownloadOptionsQuantDownloadButton.svelte';
+
+/**
+ * **ModelsDiscoverDetailsDownloadOptionsDownloadCommand** - Terminal command
+ *
+ * The `llama serve -hf ...` command box with inline quant selects and a copy
+ * button; owns its picks, nothing two-way binds them to the quant chips.
+ */
+export { default as ModelsDiscoverDetailsDownloadOptionsDownloadCommand } from './ModelsDiscoverDetailsDownloadOptionsDownloadCommand.svelte';
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsHeader.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsHeader.svelte
new file mode 100644
index 0000000000..a216283436
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsHeader.svelte
@@ -0,0 +1,94 @@
+<script lang="ts">
+	import ModelCapabilityIcons from '../../ModelCapabilityIcons.svelte';
+	import ModelsDiscoverAvatar from '../ModelsDiscoverAvatar.svelte';
+	import ModelsDiscoverDetailsHfHubStats from './ModelsDiscoverDetailsHfHubStats.svelte';
+	import ModelsDiscoverDetailsMetadata from './ModelsDiscoverDetailsMetadata.svelte';
+	import { ExternalLink } from '@lucide/svelte';
+	import { base } from '$app/paths';
+	import { ICON_CLASS_SM } from '$lib/constants';
+	import { HuggingFaceService } from '$lib/services';
+	import type { HfModelDetailInfo, HfModelGguf } from '$lib/types/huggingface';
+	import { orgOf } from '$lib/utils';
+
+	interface Props {
+		modelId: string;
+		details: HfModelDetailInfo;
+		gguf?: HfModelGguf;
+		baseModels: string[];
+		licenseTag: string | null;
+		hasVision: boolean;
+		hasTools: boolean;
+		hasReasoning: boolean;
+	}
+
+	let { baseModels, details, gguf, hasReasoning, hasTools, hasVision, licenseTag, modelId }: Props =
+		$props();
+
+	// Avatar shows the base model's org (e.g. the Qwen logo for a ggml-org GGUF)
+	// with the quant org as a corner badge when they differ.
+	let repoOrg = $derived(orgOf(details.id) || orgOf(modelId));
+	let baseOrg = $derived(orgOf(baseModels[0]));
+	let avatarOrg = $derived(baseOrg || repoOrg);
+	let quantOrg = $derived(baseOrg && baseOrg !== repoOrg ? repoOrg : undefined);
+</script>
+
+<header class="space-y-3">
+	<div class="flex items-start justify-between gap-3">
+		<div class="flex min-w-0 items-center gap-2">
+			<ModelsDiscoverAvatar
+				org={avatarOrg}
+				{quantOrg}
+				quantPositionClass="-bottom-1.5 -right-1.5"
+				quantSize="h-6 w-6"
+				size="h-12 w-12"
+			/>
+
+			<div class="min-w-0">
+				<div class="flex items-center gap-2">
+					<h1 class="truncate text-lg font-semibold">{details.id ?? modelId}</h1>
+
+					<ModelCapabilityIcons
+						gapClass="gap-2"
+						iconSize="h-4 w-4"
+						modalities={{ audio: false, video: false, vision: hasVision }}
+						supportsThinking={hasReasoning}
+						supportsToolUse={hasTools}
+					/>
+				</div>
+
+				{#if baseModels.length}
+					<div class="flex items-center gap-1">
+						<span class="truncate text-xs text-muted-foreground">{baseModels.join(', ')}</span>
+
+						<a
+							aria-label="View base model on HuggingFace"
+							class="shrink-0 text-muted-foreground transition-colors hover:text-foreground"
+							href={HuggingFaceService.getModelUrl(baseModels[0])}
+							rel="noopener noreferrer"
+							target="_blank"
+						>
+							<ExternalLink class="h-3 w-3" />
+						</a>
+					</div>
+				{/if}
+			</div>
+		</div>
+
+		<a
+			class="inline-flex shrink-0 items-center gap-1.5 rounded-md border border-border/30 px-2.5 py-1.5 text-xs font-medium shadow-sm transition-colors hover:bg-muted dark:border-border/20"
+			href={HuggingFaceService.getModelUrl(modelId)}
+			rel="noopener noreferrer"
+			target="_blank"
+		>
+			<img alt="" class="h-3.5 w-3.5" src="{base}/recommended-mcp/huggingface.ico" />
+
+			View on Hugging Face
+
+			<ExternalLink class={ICON_CLASS_SM} />
+		</a>
+	</div>
+
+	<ModelsDiscoverDetailsHfHubStats {details} />
+
+	<ModelsDiscoverDetailsMetadata {details} {gguf} {licenseTag} {modelId} />
+</header>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsHfHubStats.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsHfHubStats.svelte
new file mode 100644
index 0000000000..b848a9bfeb
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsHfHubStats.svelte
@@ -0,0 +1,31 @@
+<script lang="ts">
+	import { Download, Heart } from '@lucide/svelte';
+	import { HuggingFaceService } from '$lib/services';
+	import type { HfModelDetailInfo } from '$lib/types/huggingface';
+
+	interface Props {
+		details: HfModelDetailInfo;
+	}
+
+	let { details }: Props = $props();
+</script>
+
+<div class="flex flex-wrap items-center gap-x-4 gap-y-1 text-sm text-muted-foreground">
+	{#if typeof details.downloads === 'number'}
+		<span class="inline-flex items-center gap-1.5">
+			<Download class="h-3.5 w-3.5" />
+			{HuggingFaceService.formatDownloads(details.downloads)}
+		</span>
+	{/if}
+
+	{#if typeof details.likes === 'number'}
+		<span class="inline-flex items-center gap-1.5">
+			<Heart class="h-3.5 w-3.5" />
+			{HuggingFaceService.formatLikes(details.likes)}
+		</span>
+	{/if}
+
+	{#if details.lastModified}
+		<span>Updated {HuggingFaceService.formatRelativeTime(details.lastModified)}</span>
+	{/if}
+</div>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsMetadata.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsMetadata.svelte
new file mode 100644
index 0000000000..9f0184ac9f
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsMetadata.svelte
@@ -0,0 +1,80 @@
+<script lang="ts">
+	import ModelsDiscoverChatTemplateDialog from './ModelsDiscoverChatTemplateDialog.svelte';
+	import ModelsDiscoverDetailsMetadataItem from './ModelsDiscoverDetailsMetadataItem.svelte';
+	import { MessageSquareCode } from '@lucide/svelte';
+	import { modelsDiscoverStore } from '$lib/stores';
+	import type { HfModelDetailInfo, HfModelGguf } from '$lib/types/huggingface';
+	import { formatParameters } from '$lib/utils';
+
+	interface Props {
+		/** Full HuggingFace model id, e.g. `ggml-org/gemma-3-4b-it-GGUF`. */
+		modelId: string;
+		details: HfModelDetailInfo;
+		gguf?: HfModelGguf;
+		licenseTag: string | null;
+	}
+
+	let { details, gguf, licenseTag, modelId }: Props = $props();
+
+	// Catalog family description when curated, else the HF card description.
+	let description = $derived(
+		modelsDiscoverStore.descriptionFor(modelId) ?? details.cardData?.description
+	);
+
+	let chatTemplateOpen = $state(false);
+</script>
+
+{#if description}
+	<p class="text-sm text-muted-foreground">{description}</p>
+{/if}
+
+<!-- Metadata chips: label | value pairs, matching the HF model page style -->
+<div class="flex flex-wrap items-center gap-1.5">
+	{#if gguf?.total}
+		<ModelsDiscoverDetailsMetadataItem
+			label="Model size"
+			value="{formatParameters(gguf.total)} params"
+		/>
+	{/if}
+
+	{#if gguf?.context_length}
+		<ModelsDiscoverDetailsMetadataItem
+			label="Context"
+			value={gguf.context_length.toLocaleString()}
+		/>
+	{/if}
+
+	{#if gguf?.architecture}
+		<ModelsDiscoverDetailsMetadataItem label="Architecture" value={gguf.architecture} />
+	{/if}
+
+	{#if gguf?.chat_template}
+		<button
+			class="inline-flex items-center gap-1.5 rounded-md border border-border/30 px-2.5 py-1 text-xs font-medium shadow-sm transition-colors hover:bg-muted dark:border-border/20"
+			onclick={() => (chatTemplateOpen = true)}
+			type="button"
+		>
+			<MessageSquareCode class="h-3 w-3" />
+			Chat template
+		</button>
+	{/if}
+
+	{#if licenseTag}
+		<ModelsDiscoverDetailsMetadataItem label="License" value={licenseTag} />
+	{/if}
+
+	{#if details.gated === true}
+		<span
+			class="rounded bg-yellow-500/10 px-2 py-0.5 text-xs font-medium text-yellow-600 dark:text-yellow-400"
+		>
+			gated
+		</span>
+	{/if}
+</div>
+
+{#if gguf?.chat_template}
+	<ModelsDiscoverChatTemplateDialog
+		bind:open={chatTemplateOpen}
+		chatTemplate={gguf.chat_template}
+	/>
+{/if}
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsMetadataItem.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsMetadataItem.svelte
new file mode 100644
index 0000000000..90c3c4c74f
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsMetadataItem.svelte
@@ -0,0 +1,17 @@
+<script lang="ts">
+	interface Props {
+		label: string;
+		value: string;
+	}
+
+	let { label, value }: Props = $props();
+</script>
+
+<!-- Metadata chip: label | value pair, matching the HF model page style -->
+<span
+	class="inline-flex items-center divide-x divide-border rounded-md border border-border/30 text-xs shadow-sm dark:border-border/20"
+>
+	<span class="px-2.5 py-1 text-muted-foreground">{label}</span>
+
+	<span class="px-2.5 py-1 font-medium">{value}</span>
+</span>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsReadme.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsReadme.svelte
new file mode 100644
index 0000000000..fbf043b797
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsReadme.svelte
@@ -0,0 +1,17 @@
+<script lang="ts">
+	import { MarkdownContent } from '$lib/components/app';
+
+	interface Props {
+		readme: string | null;
+	}
+
+	let { readme }: Props = $props();
+</script>
+
+{#if readme}
+	<section
+		class="p-3 rounded-3xl border border-border/30 bg-muted/60 shadow-sm dark:border-border/20"
+	>
+		<MarkdownContent allowHtml class="prose-sm max-w-none" content={readme} />
+	</section>
+{/if}
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsSkeleton.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsSkeleton.svelte
new file mode 100644
index 0000000000..030d90fa58
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/ModelsDiscoverDetailsSkeleton.svelte
@@ -0,0 +1,93 @@
+<script lang="ts">
+	import { Skeleton } from '$lib/components/ui/skeleton';
+</script>
+
+<!-- Static skeleton of ModelsDiscoverDetails: header, metadata chips, download options and readme lines. -->
+<div class="space-y-6 p-6" data-slot="model-details-skeleton">
+	<!-- Header: avatar, name with capability icons, base model line, HF link -->
+	<div class="space-y-3">
+		<div class="flex items-start justify-between gap-3">
+			<div class="flex min-w-0 items-center gap-2">
+				<Skeleton class="h-12 w-12 rounded-md" />
+
+				<div class="min-w-0 space-y-1.5">
+					<Skeleton class="h-5 w-56 max-w-full" />
+
+					<Skeleton class="h-3 w-40 max-w-full" />
+				</div>
+			</div>
+
+			<Skeleton class="h-7.5 w-44 shrink-0 rounded-md" />
+		</div>
+
+		<!-- downloads / likes / last updated -->
+		<div class="flex items-center gap-4">
+			<Skeleton class="h-3.5 w-16" />
+
+			<Skeleton class="h-3.5 w-12" />
+
+			<Skeleton class="h-3.5 w-24" />
+		</div>
+
+		<!-- metadata chips -->
+		<div class="space-y-3">
+			<div class="flex flex-wrap items-center gap-1.5">
+				<Skeleton class="h-7 w-36 rounded-md" />
+
+				<Skeleton class="h-7 w-28 rounded-md" />
+
+				<Skeleton class="h-7 w-32 rounded-md" />
+
+				<Skeleton class="h-7 w-24 rounded-md" />
+			</div>
+		</div>
+	</div>
+
+	<!-- Download options: quant rows, CTA, terminal command -->
+	<div
+		class="rounded-3xl border border-border/30 bg-muted/40 p-4 shadow-sm dark:border-border/20 dark:bg-muted/50"
+	>
+		<div class="space-y-3 divide-y divide-border/50 dark:divide-border/35 pb-1">
+			{#each [0, 1, 2] as _, index (index)}
+				<div class="grid grid-cols-[5rem_1fr] items-start gap-3 py-3">
+					<div class="space-y-1.5 pt-1">
+						<Skeleton class="h-4 w-14" />
+
+						<Skeleton class="h-2.5 w-24" />
+					</div>
+
+					<div class="flex flex-wrap items-center justify-end gap-1.5">
+						<Skeleton class="h-6 w-28 rounded-md" />
+
+						<Skeleton class="h-6 w-20 rounded-md" />
+					</div>
+				</div>
+			{/each}
+		</div>
+
+		<div class="space-y-2.5 border-t border-border/50 pt-3.5 dark:border-border/35">
+			<Skeleton class="h-9 w-full rounded-md" />
+
+			<div class="flex items-center gap-3">
+				<span class="h-px flex-1 bg-border/50"></span>
+
+				<Skeleton class="h-3 w-44" />
+
+				<span class="h-px flex-1 bg-border/50"></span>
+			</div>
+
+			<Skeleton class="h-11 w-full rounded-md" />
+		</div>
+	</div>
+
+	<!-- Readme -->
+	<div class="space-y-2.5">
+		<Skeleton class="h-3.5 w-full" />
+
+		<Skeleton class="h-3.5 w-full" />
+
+		<Skeleton class="h-3.5 w-5/6" />
+
+		<Skeleton class="h-3.5 w-2/3" />
+	</div>
+</div>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/index.ts b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/index.ts
new file mode 100644
index 0000000000..2420bd5ef2
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDetails/index.ts
@@ -0,0 +1,72 @@
+/**
+ *
+ * MODELS DISCOVER - DETAILS
+ *
+ * The right-hand detail pane of the discover view: header (avatar, name, stats, metadata
+ * chips, capability badges), the download options area and the model-card README.
+ *
+ */
+
+/**
+ * **ModelsDiscoverDetails** - Model detail view
+ *
+ * Detail pane for the selected model. Loads its own data (details + GGUF file
+ * list) from HuggingFaceService based on the `modelId` route param.
+ */
+export { default as ModelsDiscoverDetails } from './ModelsDiscoverDetails.svelte';
+
+/**
+ * **ModelsDiscoverDetailsHeader** - Detail view header
+ *
+ * Shows the model avatar (base org + quant org corner badge), name, base model
+ * info, stats, metadata chips and capability badges.
+ */
+export { default as ModelsDiscoverDetailsHeader } from './ModelsDiscoverDetailsHeader.svelte';
+
+/**
+ * **ModelsDiscoverDetailsHfHubStats** - HuggingFace Hub stats row
+ *
+ * Downloads, likes and last-updated for the viewed model, formatted the way
+ * the Hub shows them.
+ */
+export { default as ModelsDiscoverDetailsHfHubStats } from './ModelsDiscoverDetailsHfHubStats.svelte';
+
+/**
+ * **ModelsDiscoverDetailsSkeleton** - Detail view loading skeleton
+ *
+ * Static placeholder matching the detail layout: header with avatar and name,
+ * metadata chips, the download options box and readme text lines.
+ */
+export { default as ModelsDiscoverDetailsSkeleton } from './ModelsDiscoverDetailsSkeleton.svelte';
+
+/**
+ * **ModelsDiscoverDetailsReadme** - Detail view README
+ *
+ * Renders the model card README as markdown.
+ */
+export { default as ModelsDiscoverDetailsReadme } from './ModelsDiscoverDetailsReadme.svelte';
+
+/**
+ * **ModelsDiscoverDetailsMetadata** - Detail view metadata row
+ *
+ * The detail view's metadata chips (model size, context, architecture, license,
+ * chat template).
+ */
+export { default as ModelsDiscoverDetailsMetadata } from './ModelsDiscoverDetailsMetadata.svelte';
+
+/**
+ * **ModelsDiscoverDetailsMetadataItem** - Single metadata chip
+ *
+ * One label | value chip of the detail view's metadata row (model size,
+ * context, architecture, license).
+ */
+export { default as ModelsDiscoverDetailsMetadataItem } from './ModelsDiscoverDetailsMetadataItem.svelte';
+
+/**
+ * **ModelsDiscoverChatTemplateDialog** - Chat template viewer
+ *
+ * Shows the model's chat template in a scrollable dialog with a copy button.
+ */
+export { default as ModelsDiscoverChatTemplateDialog } from './ModelsDiscoverChatTemplateDialog.svelte';
+
+export * from './ModelsDiscoverDetailsDownloadOptions';
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDownloadProgressBar.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDownloadProgressBar.svelte
index c3a89c0ba4..6f4973c12e 100644
--- a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDownloadProgressBar.svelte
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverDownloadProgressBar.svelte
@@ -18,14 +18,14 @@
 {#if overlay}
 	<div class="pointer-events-none absolute inset-x-0 bottom-0 h-0.5 overflow-hidden rounded-b-sm">
 		<div
-			class="h-full animate-pulse bg-primary transition-[width] duration-200 ease-out"
+			class="h-full bg-primary transition-[width] duration-200 ease-out"
 			style="width: {percent}%"
 		></div>
 	</div>
 {:else}
 	<div class="h-1 w-full overflow-hidden rounded-full bg-muted">
 		<div
-			class="h-full animate-pulse bg-primary transition-[width] duration-200 ease-out"
+			class="h-full bg-primary transition-[width] duration-200 ease-out"
 			style="width: {percent}%"
 		></div>
 	</div>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverList.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverList.svelte
new file mode 100644
index 0000000000..5ebff7230d
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverList.svelte
@@ -0,0 +1,41 @@
+<script lang="ts">
+	import ModelsDiscoverListItem from './ModelsDiscoverListItem.svelte';
+	import ModelsDiscoverListItemSkeleton from './ModelsDiscoverListItemSkeleton.svelte';
+	import type { HfModelInfo } from '$lib/types/huggingface';
+
+	interface Props {
+		models: HfModelInfo[];
+		activeId?: string | null;
+		loading?: boolean;
+		loadingSkeletonRowsCount?: number;
+		/** Show the original (base) model's org avatar instead of the repo's org. */
+		showBaseModelAvatar?: boolean;
+		onSelect?: (modelId: string) => void;
+	}
+
+	let {
+		activeId = null,
+		loading = false,
+		loadingSkeletonRowsCount = 8,
+		models,
+		onSelect,
+		showBaseModelAvatar = false
+	}: Props = $props();
+</script>
+
+<ul class="space-y-0.5">
+	{#if loading}
+		{#each Array(loadingSkeletonRowsCount) as _, index (index)}
+			<ModelsDiscoverListItemSkeleton {index} />
+		{/each}
+	{:else}
+		{#each models as model (model.id)}
+			<ModelsDiscoverListItem
+				active={model.id === activeId}
+				{model}
+				{onSelect}
+				{showBaseModelAvatar}
+			/>
+		{/each}
+	{/if}
+</ul>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListItem.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListItem.svelte
new file mode 100644
index 0000000000..3a496fd22f
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListItem.svelte
@@ -0,0 +1,129 @@
+<script lang="ts">
+	import ModelId from '../../ModelId.svelte';
+	import ModelsDiscoverAvatar from '../ModelsDiscoverAvatar.svelte';
+	import { HF_MMPROJ_FILENAME_TOKEN, HF_MODALITY_PIPELINE_TAGS } from '$lib/constants';
+	import { HuggingFaceService } from '$lib/services';
+	import { modelsDiscoverStore } from '$lib/stores';
+	import type { ModelsDiscoverSizeRange } from '$lib/stores/models-discover/index.svelte';
+	import type { HfModelInfo } from '$lib/types/huggingface';
+	import type { ModelModalities, ModelSidecarBadge } from '$lib/types/models';
+	import { detectThinkingSupport, detectToolUseSupport, isAuxSidecar, orgOf } from '$lib/utils';
+	import { SvelteMap } from 'svelte/reactivity';
+
+	interface Props {
+		model: HfModelInfo;
+		active?: boolean;
+		/** Show the original (base) model's org avatar instead of the repo's org. */
+		showBaseModelAvatar?: boolean;
+		onSelect?: (modelId: string) => void;
+	}
+
+	let { active = false, model, onSelect, showBaseModelAvatar = false }: Props = $props();
+
+	let org = $derived(orgOf(model.id));
+
+	// Org whose avatar is shown: the base model's org when showBaseModelAvatar
+	// (e.g. the Qwen logo for ggml-org/Qwen3.8-27B-GGUF), else the repo's org.
+	let avatarOrg = $derived.by(() => {
+		if (!showBaseModelAvatar) return org;
+
+		return orgOf(HuggingFaceService.getBaseModels(model)[0]) || org;
+	});
+
+	let contextLength = $derived(model.gguf?.context_length);
+
+	// Reasoning support from the chat template, matching the details view.
+	let supportsThinking = $derived(detectThinkingSupport(model.gguf?.chat_template ?? ''));
+
+	// Tool use support from the chat template.
+	let supportsToolUse = $derived(detectToolUseSupport(model.gguf?.chat_template ?? ''));
+
+	// Modalities derived from HF metadata: vision from an mmproj sidecar or a
+	// multimodal pipeline tag, audio/video from their pipeline tags.
+	let modalities = $derived.by<ModelModalities>(() => {
+		const tag = model.pipeline_tag ?? '';
+		const vision =
+			HF_MODALITY_PIPELINE_TAGS.vision.includes(tag) ||
+			Boolean(
+				model.siblings?.some((s) => s.rfilename.toLowerCase().includes(HF_MMPROJ_FILENAME_TOKEN))
+			);
+		const audio = HF_MODALITY_PIPELINE_TAGS.audio.includes(tag);
+		const video = HF_MODALITY_PIPELINE_TAGS.video.includes(tag);
+
+		return { audio, video, vision };
+	});
+
+	// Draft sidecars (mtp, dflash, dspark, eagle3) present in the repo, e.g.
+	// speculative-decoding drafts. mmproj is excluded: it is vision, already
+	// conveyed by the modalities.
+	let draftSidecars = $derived.by<ModelSidecarBadge[]>(() => {
+		const badges = new SvelteMap<string, ModelSidecarBadge>();
+
+		for (const sibling of model.siblings ?? []) {
+			const meta = HuggingFaceService.extractQuantMeta(sibling.rfilename);
+
+			if (!meta?.sidecar || isAuxSidecar(meta.sidecar)) continue;
+
+			const badge: ModelSidecarBadge = { kind: meta.sidecar, quant: meta.quant, repo: model.id };
+
+			badges.set(`${badge.kind}:${badge.quant ?? ''}`, badge);
+		}
+
+		return [...badges.values()];
+	});
+
+	// Min/max size across the repo's quants, draft sidecars included. The store
+	// has catalog rows covered already; any other row (a search hit) measures
+	// its repo once here and the result is cached per repo.
+	let measuredSize = $state<ModelsDiscoverSizeRange | null>(null);
+	let sizeRange = $derived(modelsDiscoverStore.cachedSizeRangeFor(model.id) ?? measuredSize);
+
+	$effect(() => {
+		const id = model.id;
+
+		if (modelsDiscoverStore.cachedSizeRangeFor(id)) return;
+
+		let cancelled = false;
+
+		void modelsDiscoverStore.sizeRange(id).then((range) => {
+			if (!cancelled) measuredSize = range ?? null;
+		});
+
+		return () => {
+			cancelled = true;
+		};
+	});
+</script>
+
+<li>
+	<button
+		aria-current={active ? 'page' : undefined}
+		class="flex w-full cursor-pointer items-start gap-2.5 rounded-lg p-2.5 text-left transition-colors {active
+			? 'bg-primary/10 hover:bg-primary/15'
+			: 'hover:bg-muted/60'}"
+		onclick={() => onSelect?.(model.id)}
+		type="button"
+	>
+		<ModelsDiscoverAvatar
+			class="mt-1"
+			org={avatarOrg}
+			quantOrg={showBaseModelAvatar ? org : undefined}
+		/>
+
+		<span class="min-w-0 flex-1">
+			<ModelId
+				class="min-w-0"
+				{contextLength}
+				{draftSidecars}
+				hideOrgName
+				iconsOnNewLine
+				{modalities}
+				modelId={model.id}
+				{sizeRange}
+				{supportsThinking}
+				{supportsToolUse}
+				wrap
+			/>
+		</span>
+	</button>
+</li>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListItemSkeleton.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListItemSkeleton.svelte
new file mode 100644
index 0000000000..851abc5238
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListItemSkeleton.svelte
@@ -0,0 +1,39 @@
+<script lang="ts">
+	import { Skeleton } from '$lib/components/ui/skeleton';
+
+	interface Props {
+		/** Row index; varies skeleton widths so the list does not look mechanical. */
+		index?: number;
+	}
+
+	let { index = 0 }: Props = $props();
+
+	// Deterministic width variations keyed by row position.
+	const NAME_WIDTHS = ['w-40', 'w-52', 'w-44', 'w-56'];
+	const BADGE_WIDTHS = [
+		['w-12', 'w-14', 'w-10'],
+		['w-16', 'w-12', 'w-12'],
+		['w-10', 'w-16', 'w-10'],
+		['w-14', 'w-10', 'w-14']
+	];
+
+	let nameWidth = $derived(NAME_WIDTHS[index % NAME_WIDTHS.length]);
+	let badgeWidths = $derived(BADGE_WIDTHS[index % BADGE_WIDTHS.length]);
+</script>
+
+<!-- Static skeleton of ModelsDiscoverListItem: avatar, name and badge rows. -->
+<li>
+	<div class="flex w-full items-start gap-2.5 rounded-lg p-2.5 text-left">
+		<Skeleton class="h-9 w-9 shrink-0 rounded-md" />
+
+		<div class="min-w-0 flex-1 space-y-1.5">
+			<Skeleton class="{nameWidth} h-4 max-w-full" />
+
+			<div class="flex items-center gap-1">
+				{#each badgeWidths as width, i (i)}
+					<Skeleton class="{width} h-3.5 rounded" />
+				{/each}
+			</div>
+		</div>
+	</div>
+</li>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListSearch.svelte b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListSearch.svelte
new file mode 100644
index 0000000000..dce949a0f6
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/ModelsDiscoverListSearch.svelte
@@ -0,0 +1,26 @@
+<script lang="ts">
+	import { SearchInput } from '$lib/components/app';
+
+	interface Props {
+		value?: string;
+		/** Search callback; the parent owns debouncing. */
+		onSearch?: (query: string) => void;
+		placeholder?: string;
+	}
+
+	let {
+		onSearch,
+		placeholder = 'Search models on Hugging Face',
+		value = $bindable('')
+	}: Props = $props();
+
+	function handleInput(next: string) {
+		value = next;
+
+		onSearch?.(value);
+	}
+</script>
+
+<div class="sticky top-0 z-99">
+	<SearchInput bind:value onInput={(v) => handleInput(v)} {placeholder} size="sm" />
+</div>
diff --git a/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/index.ts b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/index.ts
new file mode 100644
index 0000000000..d888343a15
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/ModelsDiscoverList/index.ts
@@ -0,0 +1,38 @@
+/**
+ *
+ * MODELS DISCOVER - LIST
+ *
+ * The discover sidebar column: a debounced search field above a navigable list of
+ * HuggingFace GGUF models, with skeleton rows while loading.
+ *
+ */
+
+/**
+ * **ModelsDiscoverList** - Sidebar model list
+ *
+ * Renders the discover model list as a navigable column. Each row links to the
+ * model's detail and highlights the active one.
+ */
+export { default as ModelsDiscoverList } from './ModelsDiscoverList.svelte';
+
+/**
+ * **ModelsDiscoverListSearch** - Sidebar search input
+ *
+ * Debounced search field for the model list.
+ */
+export { default as ModelsDiscoverListSearch } from './ModelsDiscoverListSearch.svelte';
+
+/**
+ * **ModelsDiscoverListItem** - Single sidebar row
+ *
+ * One model entry in the discover sidebar list, selectable via `onSelect`.
+ */
+export { default as ModelsDiscoverListItem } from './ModelsDiscoverListItem.svelte';
+
+/**
+ * **ModelsDiscoverListItemSkeleton** - Skeleton sidebar row
+ *
+ * Pulsing placeholder matching a ModelsDiscoverListItem row, shown while the
+ * list is loading.
+ */
+export { default as ModelsDiscoverListItemSkeleton } from './ModelsDiscoverListItemSkeleton.svelte';
diff --git a/tools/ui/src/lib/components/app/models/discover/index.ts b/tools/ui/src/lib/components/app/models/discover/index.ts
new file mode 100644
index 0000000000..5926b75153
--- /dev/null
+++ b/tools/ui/src/lib/components/app/models/discover/index.ts
@@ -0,0 +1,39 @@
+/**
+ *
+ * MODELS DISCOVER
+ *
+ * Components for the Models Discover view: a sidebar search + list of
+ * HuggingFace GGUF models and a detail view for the selected model, used as the
+ * body of the discovery dialog. The list and detail trees live in their own
+ * subfolders; this barrel re-exports them alongside the shared leaves.
+ *
+ */
+
+/**
+ * **ModelsDiscover** - Models discover explorer
+ *
+ * The complete discovery layout: a sidebar search + model list on the left and a
+ * detail view for the selected model on the right. Used as the body of the
+ * discovery dialog.
+ */
+export { default as ModelsDiscover } from './ModelsDiscover.svelte';
+
+/**
+ * **ModelsDiscoverAvatar** - Org avatar for a model row
+ *
+ * Shows the org's avatar image, falling back to a monogram on a stable hue
+ * derived from the org name when the image fails to load. Shared by the list,
+ * the detail header and the model selector rows.
+ */
+export { default as ModelsDiscoverAvatar } from './ModelsDiscoverAvatar.svelte';
+
+/**
+ * **ModelsDiscoverDownloadProgressBar** - Thin download progress bar
+ *
+ * Normalizes bytes to a 0..100% bar; can pin to the bottom edge as an overlay.
+ * Shared by the quant chips and the model selector's download rows.
+ */
+export { default as ModelsDiscoverDownloadProgressBar } from './ModelsDiscoverDownloadProgressBar.svelte';
+
+export * from './ModelsDiscoverList';
+export * from './ModelsDiscoverDetails';
diff --git a/tools/ui/src/lib/components/ui/select/select-content.svelte b/tools/ui/src/lib/components/ui/select/select-content.svelte
index f8792f8a9d..a8263819a1 100644
--- a/tools/ui/src/lib/components/ui/select/select-content.svelte
+++ b/tools/ui/src/lib/components/ui/select/select-content.svelte
@@ -88,7 +88,7 @@
 	<SelectPrimitive.Content
 		bind:ref
 		class={cn(
-			'relative z-[var(--layer-popover,1000000)] max-h-(--bits-select-content-available-height) min-w-[8rem] origin-(--bits-select-content-transform-origin) overflow-x-hidden overflow-y-auto rounded-md border bg-popover text-popover-foreground shadow-md data-[side=bottom]:translate-y-1 data-[side=bottom]:slide-in-from-top-2 data-[side=left]:-translate-x-1 data-[side=left]:slide-in-from-right-2 data-[side=right]:translate-x-1 data-[side=right]:slide-in-from-left-2 data-[side=top]:-translate-y-1 data-[side=top]:slide-in-from-bottom-2 data-[state=closed]:animate-out data-[state=closed]:fade-out-0 data-[state=closed]:fill-mode-forwards data-[state=closed]:zoom-out-95 data-[state=open]:animate-in data-[state=open]:fade-in-0 data-[state=open]:zoom-in-95',
+			'relative z-[var(--layer-popover,1000000)] max-h-(--bits-select-content-available-height) min-w-[8rem] origin-(--bits-select-content-transform-origin) overflow-x-hidden overflow-y-auto rounded-md border border-border bg-popover dark:border-border/20 text-popover-foreground shadow-md data-[side=bottom]:translate-y-1 data-[side=bottom]:slide-in-from-top-2 data-[side=left]:-translate-x-1 data-[side=left]:slide-in-from-right-2 data-[side=right]:translate-x-1 data-[side=right]:slide-in-from-left-2 data-[side=top]:-translate-y-1 data-[side=top]:slide-in-from-bottom-2 data-[state=closed]:animate-out data-[state=closed]:fade-out-0 data-[state=closed]:fill-mode-forwards data-[state=closed]:zoom-out-95 data-[state=open]:animate-in data-[state=open]:fade-in-0 data-[state=open]:zoom-in-95',
 			className
 		)}
 		data-slot="select-content"
@@ -99,7 +99,7 @@
 
 		<SelectPrimitive.Viewport
 			class={cn(
-				'h-(--bits-select-anchor-height) w-full min-w-(--bits-select-anchor-width) scroll-my-1 p-1'
+				'h-(--bits-select-anchor-height) w-full min-w-(--bits-select-anchor-width) scroll-my-1 p-1.5'
 			)}
 		>
 			{@render children?.()}
diff --git a/tools/ui/src/lib/components/ui/select/select-trigger.svelte b/tools/ui/src/lib/components/ui/select/select-trigger.svelte
index 9f642819ec..de3abcdf21 100644
--- a/tools/ui/src/lib/components/ui/select/select-trigger.svelte
+++ b/tools/ui/src/lib/components/ui/select/select-trigger.svelte
@@ -11,20 +11,26 @@
 		variant = 'default',
 		...restProps
 	}: WithoutChild<SelectPrimitive.TriggerProps> & {
-		size?: 'sm' | 'default';
+		size?: 'xs' | 'sm' | 'default';
 		variant?: 'default' | 'plain';
 	} = $props();
 
+	// Super small trigger: fits its selected value, for dense inline use.
+	const xsClasses =
+		"group flex h-6 w-fit items-center justify-between gap-1 rounded-md border border-border/30 bg-muted/60 px-2 py-0 text-xs whitespace-nowrap outline-none select-none transition-colors hover:bg-muted/80 focus-visible:border-ring focus-visible:ring-[3px] focus-visible:ring-ring/50 disabled:cursor-not-allowed disabled:opacity-50 data-[placeholder]:text-muted-foreground dark:border-border/20 dark:bg-muted/75 dark:hover:bg-muted [&_svg]:pointer-events-none [&_svg]:shrink-0 [&_svg:not([class*='text-'])]:text-muted-foreground";
+
 	const baseClasses = $derived(
 		variant === 'plain'
 			? "group inline-flex w-full items-center justify-end gap-2 whitespace-nowrap px-0 py-0 text-sm font-medium text-muted-foreground transition-colors focus-visible:outline-none focus-visible:ring-0 focus-visible:ring-offset-0 disabled:cursor-not-allowed disabled:opacity-50 data-[placeholder]:text-muted-foreground data-[size=default]:h-9 data-[size=sm]:h-8 [&_svg]:pointer-events-none [&_svg]:shrink-0 [&_svg:not([class*='size-'])]:size-3 [&_svg:not([class*='text-'])]:text-muted-foreground"
-			: "flex w-fit items-center justify-between gap-2 rounded-md border border-input bg-transparent px-3 py-2 text-sm whitespace-nowrap shadow-xs transition-[color,box-shadow] outline-none select-none focus-visible:border-ring focus-visible:ring-[3px] focus-visible:ring-ring/50 disabled:cursor-not-allowed disabled:opacity-50 aria-invalid:border-destructive aria-invalid:ring-destructive/20 data-[placeholder]:text-muted-foreground data-[size=default]:h-9 data-[size=sm]:h-8 *:data-[slot=select-value]:line-clamp-1 *:data-[slot=select-value]:flex *:data-[slot=select-value]:items-center *:data-[slot=select-value]:gap-2 dark:bg-input/30 dark:hover:bg-input/50 dark:aria-invalid:ring-destructive/40 [&_svg]:pointer-events-none [&_svg]:shrink-0 [&_svg:not([class*='size-'])]:size-4 [&_svg:not([class*='text-'])]:text-muted-foreground"
+			: size === 'xs'
+				? xsClasses
+				: "flex w-fit items-center justify-between gap-2 rounded-md border border-border/30 bg-muted/60 px-3 py-2 text-sm whitespace-nowrap shadow-sm transition-colors outline-none select-none hover:bg-muted/80 focus-visible:border-ring focus-visible:ring-[3px] focus-visible:ring-ring/50 disabled:cursor-not-allowed disabled:opacity-50 aria-invalid:border-destructive aria-invalid:ring-destructive/20 data-[placeholder]:text-muted-foreground data-[size=default]:h-9 data-[size=sm]:h-8 *:data-[slot=select-value]:line-clamp-1 *:data-[slot=select-value]:flex *:data-[slot=select-value]:items-center *:data-[slot=select-value]:gap-2 dark:border-border/20 dark:bg-muted/75 dark:hover:bg-muted dark:aria-invalid:ring-destructive/40 [&_svg]:pointer-events-none [&_svg]:shrink-0 [&_svg:not([class*='size-'])]:size-3.5 [&_svg:not([class*='text-'])]:text-muted-foreground"
 	);
 
 	const chevronClasses = $derived(
-		variant === 'plain'
+		variant === 'plain' || size === 'xs'
 			? 'size-3 opacity-60 transition-transform group-data-[state=open]:-rotate-180'
-			: 'size-4 opacity-50'
+			: 'size-3.5 opacity-60 transition-transform group-data-[state=open]:-rotate-180'
 	);
 </script>
 
diff --git a/tools/ui/src/lib/constants/index.ts b/tools/ui/src/lib/constants/index.ts
index 04d5ab779d..6412511736 100644
--- a/tools/ui/src/lib/constants/index.ts
+++ b/tools/ui/src/lib/constants/index.ts
@@ -47,6 +47,7 @@ export * from './path-display.constants';
 export * from './model-id.constants';
 export * from './model-loading.constants';
 export * from './models-discover.constants';
+export * from './models-discover-download.constants';
 export * from './model-compatibility.constants';
 export * from './huggingface.constants';
 export * from './precision.constants';
diff --git a/tools/ui/src/lib/constants/models-discover-download.constants.ts b/tools/ui/src/lib/constants/models-discover-download.constants.ts
new file mode 100644
index 0000000000..e38dd1efbe
--- /dev/null
+++ b/tools/ui/src/lib/constants/models-discover-download.constants.ts
@@ -0,0 +1,54 @@
+/**
+ * Models Discover - download options constants.
+ *
+ * Shared values backing the download-options area of the details pane: the
+ * serve `--spec-type` mapping, the bit-depth buckets, and the standalone
+ * command builder. Kept here (not component-local) so they sit with the rest
+ * of the discover domain constants.
+ */
+
+import type { ModelSidecar } from '$lib/constants';
+import { ModelAuxSidecar, ModelDraftSidecar } from '$lib/enums';
+
+/**
+ * `--spec-type` value for each draft sidecar; aux sidecars (mmproj, imatrix)
+ * carry none and stay empty.
+ */
+export const SPEC_TYPE: Record<ModelSidecar, string> = {
+	[ModelAuxSidecar.IMATRIX]: '',
+	[ModelAuxSidecar.MMPROJ]: '',
+	[ModelDraftSidecar.DFLASH]: 'draft-dflash',
+	[ModelDraftSidecar.DSPARK]: 'draft-dspark',
+	[ModelDraftSidecar.EAGLE3]: 'draft-eagle3',
+	[ModelDraftSidecar.MTP]: 'draft-mtp'
+};
+
+/** Bit-depth bucket for files that carry no quant token; rendered as "Other". */
+export const OTHER_BIT_DEPTH = 99;
+
+/** Label for the OTHER_BIT_DEPTH bucket. */
+export const OTHER_BIT_DEPTH_LABEL = 'Other';
+
+/** Suffix appended after a bit-depth number to label a row, e.g. `4-bit`. */
+export const BIT_DEPTH_LABEL_SUFFIX = '-bit';
+
+/**
+ * Fixed tokens of the standalone `llama serve` command preview, so the command
+ * builder and its rendered spans share one source of the CLI spelling.
+ */
+export const SERVE_COMMAND = {
+	BIN: 'llama',
+	/** Draft model repo:tag argument (download sidecar / draft weights). */
+	DRAFT_FLAG: '-hfd',
+	/** Main model repo:tag argument. */
+	MODEL_FLAG: '-hf',
+	/** Speculative-decoding type argument for the draft. */
+	SPEC_TYPE_FLAG: '--spec-type',
+	SUBCOMMAND: 'serve'
+} as const;
+
+/** Bit depth preferred for the command's default base quant. */
+export const DEFAULT_BASE_BIT_DEPTH = 4;
+
+/** Label shown for a draft-sidecar chip whose quant is unknown. */
+export const DRAFT_FILE_LABEL = 'draft';
diff --git a/tools/ui/src/lib/constants/models-discover.constants.ts b/tools/ui/src/lib/constants/models-discover.constants.ts
index f2a6a9463c..b0a0abc568 100644
--- a/tools/ui/src/lib/constants/models-discover.constants.ts
+++ b/tools/ui/src/lib/constants/models-discover.constants.ts
@@ -6,3 +6,9 @@
 
 /** llama.app model catalog used as the default model list. Online-only source; the discover feature requires an internet connection anyway. */
 export const MODELS_DISCOVER_CATALOG_URL = 'https://llama.app/v1/catalog.json';
+
+/**
+ * Catalog repos fetched in parallel per batch; small on purpose so the HF API
+ * is not hit with the whole catalog at once.
+ */
+export const MODELS_DISCOVER_CATALOG_BATCH = 4;
diff --git a/tools/ui/src/lib/enums/index.ts b/tools/ui/src/lib/enums/index.ts
index 583187d964..6b529b66e4 100644
--- a/tools/ui/src/lib/enums/index.ts
+++ b/tools/ui/src/lib/enums/index.ts
@@ -69,7 +69,13 @@ export {
 	JsonSchemaType
 } from './mcp.enums';
 
-export { ModelAuxSidecar, ModelCapability, ModelDraftSidecar, ModelModality } from './model.enums';
+export {
+	ModelAuxSidecar,
+	ModelCapability,
+	ModelDraftSidecar,
+	ModelModality,
+	ModelSelectableFileKind
+} from './model.enums';
 
 export { ModelDownloadConfirmAction, ModelDownloadStopRequest } from './model.enums';
 
diff --git a/tools/ui/src/lib/enums/model.enums.ts b/tools/ui/src/lib/enums/model.enums.ts
index f2a0cc3552..0b54ec1631 100644
--- a/tools/ui/src/lib/enums/model.enums.ts
+++ b/tools/ui/src/lib/enums/model.enums.ts
@@ -36,6 +36,16 @@ export enum ModelAuxSidecar {
 	MMPROJ = 'mmproj'
 }
 
+/**
+ * Role of a selectable GGUF in the download options: the main weights, a
+ * speculative-decoding draft sidecar, or an auxiliary sidecar (mmproj).
+ */
+export enum ModelSelectableFileKind {
+	AUX = 'aux',
+	DRAFT = 'draft',
+	MAIN = 'main'
+}
+
 /**
  * Why an in-flight download is being stopped, so the terminal `download_failed`
  * feed event can be attributed: a user pause (resumable) or a user cancel
diff --git a/tools/ui/src/lib/stores/index.ts b/tools/ui/src/lib/stores/index.ts
index b571699072..fcab8a8064 100644
--- a/tools/ui/src/lib/stores/index.ts
+++ b/tools/ui/src/lib/stores/index.ts
@@ -40,6 +40,9 @@ export { mcpStore } from './mcp/index.svelte';
 // MODELS
 export { modelsStore } from './models/index.svelte';
 
+// MODELS DISCOVER (HuggingFace browse state for the discover dialog)
+export { modelsDiscoverStore } from './models-discover/index.svelte';
+
 // SERVER
 export { serverStore } from './server.svelte';
 
diff --git a/tools/ui/src/lib/stores/models-discover/index.svelte.ts b/tools/ui/src/lib/stores/models-discover/index.svelte.ts
new file mode 100644
index 0000000000..28cc66f00d
--- /dev/null
+++ b/tools/ui/src/lib/stores/models-discover/index.svelte.ts
@@ -0,0 +1,282 @@
+/**
+ * modelsDiscoverStore - Models Discover browse state
+ *
+ * Owns the HuggingFace GGUF model list shown in the discover sidebar
+ * (the Discover tab of DialogManageModels). By default the list is the curated catalog set;
+ * search replaces it with matches across all of HuggingFace. Both paths fetch
+ * the same fields, so a row renders the same badges and sizes either way.
+ */
+
+import { MODELS_DISCOVER_CATALOG_BATCH } from '$lib/constants';
+import { HuggingFaceService } from '$lib/services';
+import type {
+	HfCatalogBuild,
+	HfCatalogEntry,
+	HfModelInfo,
+	HfModelSibling
+} from '$lib/types/huggingface';
+import { isAuxSidecar } from '$lib/utils';
+import { SvelteMap } from 'svelte/reactivity';
+
+/** Min/max GGUF file size (bytes) across the quants of one repo. */
+export interface ModelsDiscoverSizeRange {
+	max: number;
+	min: number;
+}
+
+class ModelsDiscoverStore {
+	error = $state<string | null>(null);
+	models = $state<HfModelInfo[]>([]);
+	/** First model in the list - discover auto-opens this one. */
+	firstModel = $derived(this.models[0] ?? null);
+
+	loading = $state(false);
+	/** True while a search is in flight; only the newest request owns this flag. */
+	searching = $state(false);
+
+	private catalog: HfCatalogEntry[] = [];
+	/** Repo id -> size range, for catalog rows and lazily measured search rows. */
+	private catalogSizeRanges = new SvelteMap<string, ModelsDiscoverSizeRange>();
+	private defaultModels: HfModelInfo[] = [];
+	private fetched = false;
+	private searchRequestId = 0;
+	/** In-flight `sizeRange()` lookups, keyed by repo id. */
+	private sizeRangePending = new Map<string, Promise<ModelsDiscoverSizeRange | undefined>>();
+
+	/**
+	 * Cached size range for a repo, without measuring: the synchronous part of
+	 * `sizeRange()`, for rendering a row before its measurement resolves.
+	 */
+	cachedSizeRangeFor(modelId: string): ModelsDiscoverSizeRange | undefined {
+		return this.catalogSizeRanges.get(modelId);
+	}
+
+	/**
+	 * Catalog family description for a repo id, or undefined when the repo is
+	 * not part of the catalog (e.g. a search result outside the curated list).
+	 */
+	descriptionFor(modelId: string): string | undefined {
+		return this.catalog.find((entry) =>
+			entry.sizes.some((size) => size.builds.some((build) => build.repo === modelId))
+		)?.description;
+	}
+
+	/**
+	 * Fetch the default list from the llama.app catalog, one repo per catalog
+	 * size in display order (newest family first). Every repo is fetched by ID
+	 * with its file tree, so the rows carry chat-template capabilities, context
+	 * length and a real size range - the same data a search result gets.
+	 * No-op when already loaded or in flight.
+	 */
+	async fetch(): Promise<void> {
+		if (this.loading || this.fetched) return;
+
+		this.loading = true;
+		this.error = null;
+
+		try {
+			const catalog = await HuggingFaceService.getCatalog();
+
+			this.catalog = catalog;
+
+			const builds = this.catalogBuilds();
+			const failedBuilds: HfCatalogBuild[] = [];
+
+			this.defaultModels = [];
+
+			// fetch in small batches: not every repo hits the HF API at once,
+			// and the rows land as they arrive instead of all at the end
+			for (let i = 0; i < builds.length; i += MODELS_DISCOVER_CATALOG_BATCH) {
+				const batch = await Promise.all(
+					builds.slice(i, i + MODELS_DISCOVER_CATALOG_BATCH).map(async (build) => {
+						const [info, tree] = await Promise.all([
+							HuggingFaceService.getDetails(build.repo),
+							HuggingFaceService.getTree(build.repo)
+						]);
+
+						return { build, info, tree };
+					})
+				);
+
+				for (const { build, info, tree } of batch) {
+					if (!info) {
+						failedBuilds.push(build);
+
+						continue;
+					}
+
+					this.catalogSizeRanges.set(build.repo, this.sizeRangeFor(build, tree));
+
+					// the catalog repo id, not the HF response `id`, drives selection
+					this.defaultModels.push({ ...info, id: build.repo, modelId: build.repo } as HfModelInfo);
+				}
+
+				// show what has landed, unless a search owns the list right now
+				if (!this.searching) {
+					this.models = [...this.defaultModels];
+				}
+			}
+
+			// stay incomplete when some repos failed, so the next mount retries
+			// them; succeeded repos are served from the service cache for free
+			this.fetched = failedBuilds.length === 0;
+		} catch (err) {
+			this.error = err instanceof Error ? err.message : 'Failed to fetch models';
+		} finally {
+			this.loading = false;
+		}
+	}
+
+	/** Replace the list with search results; an empty query restores the default list. */
+	async search(query: string): Promise<void> {
+		const trimmed = query.trim();
+		const requestId = ++this.searchRequestId;
+
+		if (!trimmed) {
+			this.searching = false;
+			this.models = this.defaultModels;
+			this.error = null;
+
+			return;
+		}
+
+		this.searching = true;
+
+		try {
+			const results = await HuggingFaceService.searchByQuery(trimmed, { limit: 50 });
+
+			if (requestId !== this.searchRequestId) return;
+
+			this.models = results;
+			this.error = null;
+		} catch (err) {
+			if (requestId !== this.searchRequestId) return;
+
+			this.error = err instanceof Error ? err.message : 'Search failed';
+		} finally {
+			if (requestId === this.searchRequestId) this.searching = false;
+		}
+	}
+
+	/**
+	 * Size range for a repo not measured yet - a search result, or a catalog
+	 * repo whose tree came back empty. Fetches the file tree once per repo and
+	 * caches it, so remounting a row (scrolling, searching back) is free.
+	 */
+	sizeRange(modelId: string): Promise<ModelsDiscoverSizeRange | undefined> {
+		const cached = this.catalogSizeRanges.get(modelId);
+
+		if (cached) return Promise.resolve(cached);
+
+		const pending = this.sizeRangePending.get(modelId);
+
+		if (pending) return pending;
+
+		const request = (async () => {
+			const tree = await HuggingFaceService.getTree(modelId);
+			const range = this.sizeRangeOfMainQuants(tree);
+
+			if (range) this.catalogSizeRanges.set(modelId, range);
+
+			return range;
+		})()
+			.catch(() => undefined)
+			.finally(() => this.sizeRangePending.delete(modelId));
+
+		this.sizeRangePending.set(modelId, request);
+
+		return request;
+	}
+
+	/**
+	 * Bytes of every quant the catalog lists under this repo, parsed from the
+	 * `size` strings when a build carries no `sizeBytes`. Never empty: an
+	 * unparsable entry contributes the build's own size.
+	 */
+	private buildSizeBytes(build: HfCatalogBuild): number[] {
+		const sizes = this.catalog
+			.flatMap((entry) => entry.sizes)
+			.flatMap((size) => size.builds.filter((b) => b.repo === build.repo))
+			.map((b) => b.sizeBytes ?? HuggingFaceService.parseSizeBytes(b.size))
+			.filter((bytes): bytes is number => Boolean(bytes) && bytes > 0);
+
+		return sizes.length > 0 ? sizes : [build.sizeBytes ?? 0];
+	}
+
+	/**
+	 * One build per catalog size, newest family first (by release date).
+	 * Prefers the official ggml-org repo, falling back to the first build so
+	 * families published only by other orgs (mistralai, unsloth) still show up.
+	 * Returns an empty array when the catalog is empty.
+	 */
+	private catalogBuilds(): HfCatalogBuild[] {
+		return [...this.catalog]
+			.sort((a, b) => b.released.localeCompare(a.released))
+			.flatMap((entry) =>
+				entry.sizes.flatMap((size) => {
+					const build = size.builds.find((b) => b.repo.startsWith('ggml-org/')) ?? size.builds[0];
+
+					return build ? [build] : [];
+				})
+			);
+	}
+
+	/** Byte sizes of every non-sidecar quant file in a tree, shards collapsed. */
+	private quantSizesOf(tree: HfModelSibling[]): number[] {
+		return HuggingFaceService.collapseGgufShards(
+			HuggingFaceService.filterByExtension(tree, '.gguf')
+		)
+			.filter((f) => {
+				const { quant, sidecar } = HuggingFaceService.extractQuantMeta(f.path) ?? {};
+
+				return Boolean(quant) && (sidecar === null || sidecar === undefined);
+			})
+			.map((f) => f.size ?? 0)
+			.filter((size) => size > 0);
+	}
+
+	/**
+	 * Size range of one catalog build: every quant in the repo's file tree, plus
+	 * the draft sidecars those files carry (mtp, dflash, ...) so the downloaded
+	 * model fits within the range. Falls back to the catalog `size` / `sizeBytes`
+	 * strings when the tree yielded nothing (partial fetch, sharded-only repo).
+	 */
+	private sizeRangeFor(build: HfCatalogBuild, tree: HfModelSibling[]): ModelsDiscoverSizeRange {
+		const quantSizes = this.quantSizesOf(tree);
+
+		if (quantSizes.length === 0) {
+			const listed = this.buildSizeBytes(build);
+
+			return { max: Math.max(...listed), min: Math.min(...listed) };
+		}
+
+		const draftSizes = tree
+			.filter((f) => {
+				const sidecar = HuggingFaceService.extractQuantMeta(f.path)?.sidecar;
+
+				return sidecar !== null && sidecar !== undefined && !isAuxSidecar(sidecar);
+			})
+			.map((f) => f.size ?? 0)
+			.filter((size) => size > 0);
+		const extra = draftSizes.length > 0 ? Math.max(...draftSizes) : 0;
+
+		return {
+			max: Math.max(...quantSizes) + extra,
+			min: Math.min(...quantSizes) + (draftSizes.length > 0 ? Math.min(...draftSizes) : 0)
+		};
+	}
+
+	/**
+	 * Size range across the main-model quants of a file tree, draft sidecars
+	 * excluded (they only widen the range when a row advertises them).
+	 */
+	private sizeRangeOfMainQuants(tree: HfModelSibling[]): ModelsDiscoverSizeRange | undefined {
+		const sizes = this.quantSizesOf(tree);
+
+		if (sizes.length === 0) return undefined;
+
+		return { max: Math.max(...sizes), min: Math.min(...sizes) };
+	}
+}
+
+export const modelsDiscoverStore = new ModelsDiscoverStore();
diff --git a/tools/ui/src/lib/types/index.ts b/tools/ui/src/lib/types/index.ts
index 453af9bb80..7f35a13633 100644
--- a/tools/ui/src/lib/types/index.ts
+++ b/tools/ui/src/lib/types/index.ts
@@ -111,6 +111,14 @@ export type {
 	ModalityCapabilities
 } from './models';
 
+// Models discover types
+export type {
+	ModelBitDepthRow,
+	ModelDownloadEntryState,
+	ModelQuantOption,
+	ModelSelectableFile
+} from './models-discover';
+
 // Settings types
 export type {
 	SettingsConfigValue,
diff --git a/tools/ui/src/lib/types/models-discover.d.ts b/tools/ui/src/lib/types/models-discover.d.ts
new file mode 100644
index 0000000000..f9812fea85
--- /dev/null
+++ b/tools/ui/src/lib/types/models-discover.d.ts
@@ -0,0 +1,30 @@
+import type { ModelSelectableFileKind } from '$lib/enums';
+import type { HfModelSibling } from '$lib/types/huggingface';
+
+/**
+ * Option of a quant `<select>` in the download-options command builder; the
+ * picks only compose the serve command and are not bound to the quant chips.
+ */
+export interface ModelQuantOption {
+	/** Quant token, or the file name when the file carries no quant (e.g. BF16). */
+	label: string;
+	/** Repo-relative file path the option stands for. */
+	path: string;
+}
+
+/** Download state of a single repo entry, injected by the integration layer. */
+export interface ModelDownloadEntryState {
+	/** Server identifier the entry's actions (pause / resume / cancel / retry) target. */
+	repoWithTag: string;
+	isDownloading: boolean;
+	progress: ModelDownloadProgress | null;
+	isDownloaded: boolean;
+	isPaused: boolean;
+	isFailed: boolean;
+}
+
+/** A group of GGUF files sharing one bit-depth bucket. */
+export type ModelBitDepthRow = { bitDepth: number; files: HfModelSibling[] };
+
+/** A selectable GGUF, tagged with its role: main weights, draft, or aux (mmproj). */
+export type ModelSelectableFile = HfModelSibling & { kind: ModelSelectableFileKind };