Mistral Small 22B
Mistral Small 22B loads in 17 GB at Q4_K_M, comfortably from 32 GB of memory — Macs included, starting at the MacBook Pro M5 Pro 48GB. Below is the memory math we ran for it, the cheapest card that fits, and the fastest machine we track.
How much memory does Mistral Small 22B need?
Mistral Small 22B is a 22B dense model built for coding, quality. The weights alone take 17 GB at Q4_K_M; add context and the OS, and it belongs in the 32 GB memory class. Every number below comes from the ModelFit engine — speeds are estimates, labeled est., because we do not benchmark hardware ourselves.
KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).
Which machines run Mistral Small 22B?
Verdicts come from the same engine that powers our fit checker — memory capacity first, bandwidth for speed. How we compute these numbers · Hugging Face model card
More Mistral models
Frequently asked questions
How much memory does Mistral Small 22B need?
17 GB for the Q4_K_M weights, plus ~4.0 GB of KV-cache at 16k context — about 21.0 GB total. Comfortable from 32 GB of VRAM or unified memory.
Does Mistral Small 22B run on a Mac?
Yes — from the MacBook Pro M5 Pro 48GB (~18 tok/s est.). Unified memory means the RAM budget is the only limit.
What is the cheapest GPU for Mistral Small 22B?
The AMD Radeon RX 7900 XT is the cheapest tracked card that runs Mistral Small 22B comfortably — ~31 tok/s est. at ~$550 used.
Cite this page
ModelFit: Mistral Small 22B — specs, memory math and hardware verdicts. https://modelfit.io/models/mistral-small-22b/ (dataset updated 2026-09-03, CC BY 4.0).