Can I Run Mistral Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

Superseded model. Mistral Family has been superseded by Mistral Small 4. This page is kept for reference; the newer family is a better starting point. View Mistral Small 4 →

Written by Jakub Rusinowski · Last updated January 28, 2025

Yes, but it is tight

Yes, but it is tight — Mistral Small 3 (24B) at Q6_K needs about 22.4 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.6 GB before the runtime starts swapping. Expect ~33.9 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~33.9 tok/s

RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models24 GB
Memory bandwidth1008 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

Mistral Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization

QuantMemory neededFits 24 GB?Max contextEst. speedDownload
F1650.7 GB✗ No48 GB
Q8_028.2 GB✗ No25.5 GB
Q6_K22.4 GB✓ Yes8K~33.9 tok/s19.7 GB
Q5_K_M19.7 GB✓ Yes16K~38.5 tok/s17 GB
Q4_K_M17.2 GB✓ Yes32K~44.1 tok/s14.5 GB
Q3_K_M12.9 GB✓ Yes32K~58.8 tok/s10.2 GB
Q2_K10.6 GB✓ Yes32K~71.8 tok/s7.9 GB

Which Mistral Family sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Mistral Small 3 (24B)17.2 GB✓ Fits~44.1 tok/s
Mistral NeMo 12B9.4 GB✓ Fits~78.6 tok/s

RTX 4090 desktop 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 Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

Yes, but it is tight — Mistral Small 3 (24B) at Q6_K needs about 22.4 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.6 GB before the runtime starts swapping. Expect ~33.9 tok/s (estimated), with room for about 8,192 tokens of context.

Which quantization of Mistral Family should I use on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

Q6_K — it needs about 22.4 GB of the 24 GB available, downloads as roughly 19.7 GB, and runs at an estimated 33.9 tokens/sec with up to 8K of context.

What limits Mistral Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

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 RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)

Mistral Family on GPUs

What This Model Is Good At

Model & Tools

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