Can I Run Devstral on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM)?

Written by Jakub Rusinowski · Last updated August 15, 2026

Yes, but it is tight

Yes, but it is tight — Devstral-2 22B at Q4_K_M needs about 15.7 GB of the 16 GB usable on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM), leaving only ~0.3 GB before the runtime starts swapping. Expect ~45.8 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: low · Recommended quantization: Q4_K_M · Estimated speed: ~45.8 tok/s

RTX 5080 Desktop (16 GB VRAM, 32 GB RAM) — what it gives a model

Usable memory for models16 GB
Memory bandwidth960 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

Devstral on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM): memory by quantization

QuantMemory neededFits 16 GB?Max contextEst. speedDownload
F1646.4 GB✗ No44 GB
Q8_025.8 GB✗ No23.4 GB
Q6_K20.5 GB✗ No18 GB
Q5_K_M18 GB✗ No15.6 GB
Q4_K_M15.7 GB✓ Yes8K~45.8 tok/s13.3 GB
Q3_K_M11.8 GB✓ Yes16K~61 tok/s9.4 GB
Q2_K9.6 GB✓ Yes32K~74.6 tok/s7.2 GB

Which Devstral sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Devstral-2 123B77.9 GB✗ Too large
Devstral Small 24B16.6 GB✗ Too large
Devstral-2 22B15.7 GB✓ Fits~45.8 tok/s

What to watch out for

RTX 5080 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 5080 Desktop (16 GB VRAM, 32 GB RAM)?

Yes, but it is tight — Devstral-2 22B at Q4_K_M needs about 15.7 GB of the 16 GB usable on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM), leaving only ~0.3 GB before the runtime starts swapping. Expect ~45.8 tok/s (estimated), with room for about 8,192 tokens of context.

Which quantization of Devstral should I use on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM)?

Q4_K_M — it needs about 15.7 GB of the 16 GB available, downloads as roughly 13.3 GB, and runs at an estimated 45.8 tokens/sec with up to 8K of context.

What limits Devstral on RTX 5080 Desktop (16 GB VRAM, 32 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 5080 Desktop (16 GB VRAM, 32 GB RAM)

Devstral on GPUs

What This Model Is Good At

Model & Tools

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