Mistral Small 3.1
Mistral Small 3.1 loads in 15 GB at Q4_K_M, comfortably from 32 GB of memory — Macs included, starting at the MacBook Air M5 24GB. 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 3.1 need?
Mistral Small 3.1 is a 24B dense model built for chat, coding. The weights alone take 15 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 3.1?
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
Go deeper
More Mistral models
Frequently asked questions
How much memory does Mistral Small 3.1 need?
15 GB for the Q4_K_M weights, plus ~4.0 GB of KV-cache at 16k context — about 19.0 GB total. Comfortable from 32 GB of VRAM or unified memory.
Does Mistral Small 3.1 run on a Mac?
Yes — from the MacBook Air M5 24GB (~8 tok/s est.). Unified memory means the RAM budget is the only limit.
What is the cheapest GPU for Mistral Small 3.1?
The AMD Radeon RX 7900 XT is the cheapest tracked card that runs Mistral Small 3.1 comfortably — ~29 tok/s est. at ~$550 used.
Which Mistral Small 3.1 quant should I pick?
The tracked Q4_K_M build at 15 GB is the one we recommend for most machines. Every published build, ranked by real GGUF file size rather than a formula, is on the quant comparison page linked below.
Cite this page
ModelFit: Mistral Small 3.1 — specs, memory math and hardware verdicts. https://modelfit.io/models/mistral-small-3.1/ (dataset updated 2026-09-03, CC BY 4.0).