Can I Run Mistral Small 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated March 16, 2026

Yes

Yes — Mistral Small 4 119B-A6.5B at Q6_K needs about 101.2 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB) (~26.8 GB spare), at ~9.6 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~9.6 tok/s

Framework Desktop (Ryzen AI Max+ 395, 128 GB) — what it gives a model

Usable memory for models128 GB
Memory bandwidth256 GB/s
Form factorMini PC
Operating systemWindows or Linux
Memory upgradeableNo — soldered

Mistral Small 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

QuantMemory neededFits 128 GB?Max contextEst. speedDownload
F16241.7 GB✗ No238 GB
Q8_0130.1 GB✗ No126.4 GB
Q6_K101.2 GB✓ Yes64K~9.6 tok/s97.6 GB
Q5_K_M88 GB✓ Yes64K~11 tok/s84.3 GB
Q4_K_M75.5 GB✓ Yes128K~12.7 tok/s71.8 GB
Q3_K_M54.4 GB✓ Yes128K~17.1 tok/s50.7 GB
Q2_K42.8 GB✓ Yes128K~21.1 tok/s39.1 GB

What to watch out for

Framework Desktop 128 GB limitations

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

FAQ

Can I run Mistral Small 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes — Mistral Small 4 119B-A6.5B at Q6_K needs about 101.2 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB) (~26.8 GB spare), at ~9.6 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of Mistral Small 4 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q6_K — it needs about 101.2 GB of the 128 GB available, downloads as roughly 97.6 GB, and runs at an estimated 9.6 tokens/sec with up to 64K of context.

What limits Mistral Small 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

Other Computers

Other Models on Framework Desktop (Ryzen AI Max+ 395, 128 GB)

Mistral Small 4 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Mistral Small 4 model page | Check your hardware