Can I Run Devstral on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Written by Jakub Rusinowski · Last updated August 15, 2026

Yes

Yes — Devstral Small 24B at Q8_0 needs about 27.6 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) (~4.4 GB spare), at ~46 tok/s (estimated), with room for about 32,768 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~46 tok/s

RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models32 GB
Memory bandwidth1792 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

Devstral on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization

QuantMemory neededFits 32 GB?Max contextEst. speedDownload
F1650.1 GB✗ No48 GB
Q8_027.6 GB✓ Yes32K~46 tok/s25.5 GB
Q6_K21.8 GB✓ Yes64K~57.5 tok/s19.7 GB
Q5_K_M19.2 GB✓ Yes64K~64.9 tok/s17 GB
Q4_K_M16.6 GB✓ Yes64K~73.9 tok/s14.5 GB
Q3_K_M12.4 GB✓ Yes64K~96.6 tok/s10.2 GB
Q2_K10 GB✓ Yes128K~116.1 tok/s7.9 GB

Which Devstral sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Devstral-2 123B77.9 GB✗ Too large
Devstral Small 24B16.6 GB✓ Fits~73.9 tok/s
Devstral-2 22B15.7 GB✓ Fits~78.6 tok/s

What to watch out for

RTX 5090 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 Devstral on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Yes — Devstral Small 24B at Q8_0 needs about 27.6 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) (~4.4 GB spare), at ~46 tok/s (estimated), with room for about 32,768 tokens of context.

Which quantization of Devstral should I use on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Q8_0 — it needs about 27.6 GB of the 32 GB available, downloads as roughly 25.5 GB, and runs at an estimated 46 tokens/sec with up to 32K of context.

What limits Devstral on RTX 5090 Desktop (32 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 5090 Desktop (32 GB VRAM, 64 GB RAM)

Devstral on GPUs

What This Model Is Good At

Model & Tools

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