Mistral Small 22B
Mistral Small 22B loads in 17 GB at Q4_K_M and is comfortable from 32 GB of memory, Macs included from the MacBook Pro M5 Pro 48GB. Below: the full memory math, the cheapest card that runs it well, and the fastest machine we track.
PARAMETERS
22B
FORMAT
Q4_K_M
MIN MEMORY
32 GB
BEST FOR
Coding, Quality
Memory math
Weights (Q4_K_M)
17 GB
+ KV cache (16k)
~4.0 GB
Total at 16k
~21.0 GB
Comfortable from
32 GB
KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).
Hardware snapshot
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).