Can Desktop PC · GeForce RTX 5090 · 32 GB RAM run Mistral Small 4 (119B-A6.5B)?
32 GB VRAM + 32 GB RAM · 1792 GB/s memory bandwidth · Mistral Small 4 (119B-A6.5B) has 119.4B parameters (6.5B active per token).
Short answer
No. It doesn't fit in memory.
Needs ≈56 GB but only ≈55 GB of VRAM + system RAM is available after the OS and other apps.
Why it doesn’t fit
Even its smallest practical version (Q3_K_M) needs about 56 GB for the model, its context memory and the runtime. After Windows (≈4.5 GB), a browser with a few tabs (≈3.0 GB) and Open WebUI (≈1.0 GB), Desktop PC · GeForce RTX 5090 · 32 GB RAM has about 55 GB left, so it’s 1.4 GB short.
Ways to make it work
Close everything else
With no other apps open, Mistral Small 4 (119B-A6.5B) runs at Q3_K_M: Borderline at 17–25 tok/s. Expect the system to feel tight while it’s loaded.
Pick a smaller model from the same family
Get more memory
You’d want at least 64 GB of VRAM plus RAM in total. The machines below are the cheapest that run it comfortably.
Check your exact setup
These pages assume typical settings. A shorter context or a lighter chat app can change the answer.
Check Desktop PC · GeForce RTX 5090 · 32 GB RAM
The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.
Other models for Desktop PC · GeForce RTX 5090 · 32 GB RAM
The best-rated models for chat on this machine.
- Qwen3.6 35B-A3B320–440 tok/sExcellent
- Gemma 4 26B-A4B220–300 tok/sExcellent
- LFM2.5 24B-A2B560–760 tok/sExcellent
- Qwen3.5 35B-A3B320–440 tok/sExcellent
- GLM-4.7-Flash (30B-A3B)270–370 tok/sExcellent
- gpt-oss-20b≈260 tok/sExcellent
Cheapest machines for Mistral Small 4 (119B-A6.5B)
Hardware rated comfortable or better for chat, lowest price first.
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 128 GB$2,000 · 30–40 tok/sExcellent
- Mac Studio M2 Max 96 GB$3,799 · 50–65 tok/sExcellent
- MacBook Pro M3 Max 96 GB$3,999 · 40–50 tok/sExcellent
- Mac Studio M4 Max 128 GB$4,099 · 50–70 tok/sExcellent
- Mac Studio M5 Max 128 GB$4,099 · 50–85 tok/sExcellent
- MacBook Pro M2 Max 96 GB$5,099 · 50–65 tok/sExcellent
Same chip, other memory: 64 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.