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
| Usable memory for models | 16 GB |
| Memory bandwidth | 960 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 16 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 46.4 GB | ✗ No | — | — | 44 GB |
| Q8_0 | 25.8 GB | ✗ No | — | — | 23.4 GB |
| Q6_K | 20.5 GB | ✗ No | — | — | 18 GB |
| Q5_K_M | 18 GB | ✗ No | — | — | 15.6 GB |
| Q4_K_M | 15.7 GB | ✓ Yes | 8K | ~45.8 tok/s | 13.3 GB |
| Q3_K_M | 11.8 GB | ✓ Yes | 16K | ~61 tok/s | 9.4 GB |
| Q2_K | 9.6 GB | ✓ Yes | 32K | ~74.6 tok/s | 7.2 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Devstral-2 123B | 77.9 GB | ✗ Too large | — |
| Devstral Small 24B | 16.6 GB | ✗ Too large | — |
| Devstral-2 22B | 15.7 GB | ✓ Fits | ~45.8 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
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.
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.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving