mirror of
https://github.com/ollama/ollama.git
synced 2026-09-21 13:38:14 -05:00
Jesse Gross
b68b112bd8
Loading a model can transform tensors after reading them: qwen3.5 models pack their linear-attention projections into one layout, and MoE models fuse the gate and up expert stacks. The buffers those transforms consume go back to MLX's allocator pool rather than to the system, and nothing releases the pool until the first request finishes. On qwen3.8:27b-mlx that is 2.15 GiB held idle on top of 16.9 GiB of weights, counted in the runner's reported memory the whole time. Clear the pool once the weights are evaluated. Models whose tensors load unchanged, such as gemma4, leave nothing in the pool and are unaffected.