Ministral 3 8B
Ministral 3 8B loads in 6 GB at Q4_K_M, comfortably from 12 GB of memory, Macs included, starting at the Mac Mini M6 16GB. Below is the memory math we ran for it, the cheapest card that fits, and the fastest machine we track.
How much memory does Ministral 3 8B need?
Ministral 3 8B is a 8.4B dense model built for chat, coding, vision. The weights alone take 6 GB at Q4_K_M; add context and the OS, and it belongs in the 12 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 Ministral 3 8B?
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
Get told when a better model fits your MacBook Air M5 16 GB
New open-weight models land every week. When one beats today's pick on your exact machine, you get one short email: the model, why it is better, and the command to run it.
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Frequently asked questions
How much memory does Ministral 3 8B need?
6 GB for the Q4_K_M weights, plus ~2.0 GB of KV-cache at 16k context, about 8.0 GB total. Comfortable from 12 GB of VRAM or unified memory.
Does Ministral 3 8B run on a Mac?
Yes, from the Mac Mini M6 16GB (~27 tok/s est.). Unified memory means the RAM budget is the only limit.
What is the cheapest GPU for Ministral 3 8B?
The AMD Radeon RX 7900 XT is the cheapest tracked card that runs Ministral 3 8B comfortably, ~71 tok/s est. at ~$550 used.
Cite this page
ModelFit: Ministral 3 8B, specs, memory math and hardware verdicts. https://modelfit.io/models/ministral-3-8b/ (dataset updated 2026-10-03, CC BY 4.0).