Sized at Q4_K_M with a 8K context: weights, KV cache and framework overhead, against what MacBook Pro M4, 24GB leaves free. Mistral Small 3.1 24B at Q4_K_M needs 16.4 GB and you have 18 GB available, so it fits with 1.6 GB to spare.
Mistral Small 3.1 24B at Q4_K_M needs 16.4 GB and you have 18 GB available, so it fits with 1.6 GB to spare.
Your machine is not exactly this one. Run this for your exact setup — the form opens pre-filled with MacBook Pro M4, 24GB and Mistral Small 3.1 24B.
Yes. Mistral Small 3.1 24B at Q4_K_M needs 16.4 GB and you have 18 GB available, so it fits with 1.6 GB to spare.
Yes, and it is the figure people forget. The 16.4 GB above already includes the KV cache at 8K; that cache grows roughly linearly with context, so doubling the window adds real gigabytes rather than a rounding error. If you plan to work with long documents on MacBook Pro M4, 24GB, size for the context you will actually use, not the default.
Data behind this page last checked 2025-03-17.