作者： Jakub Rusinowski · 最后更新： 2026年9月11日
Yes
Yes — Devstral Small 2505 24B at Q2_K needs about 10 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) (~2 GB spare), at ~29.5 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q2_K · Estimated speed: ~29.5 tok/s
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
| Usable memory for models | 12 GB |
| Memory bandwidth | 360 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 12 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 50.1 GB | ✗ No | — | — | 48 GB |
| Q8_0 | 27.6 GB | ✗ No | — | — | 25.5 GB |
| Q6_K | 21.8 GB | ✗ No | — | — | 19.7 GB |
| Q5_K_M | 19.2 GB | ✗ No | — | — | 17 GB |
| Q4_K_M | 16.6 GB | ✗ No | — | — | 14.5 GB |
| Q3_K_M | 12.4 GB | ✗ No | — | — | 10.2 GB |
| Q2_K | 10 GB | ✓ Yes | 16K | ~29.5 tok/s | 7.9 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Devstral-2 123B | 77.9 GB | ✗ Too large | — |
| Devstral Small 2 24B | 17 GB | ✗ Too large | — |
| Devstral Small 2505 24B | 16.6 GB | ✗ Too large | — |
| Devstral-2 22B (Unverified Listing) | 15.7 GB | ✗ Too large | — |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes — Devstral Small 2505 24B at Q2_K needs about 10 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) (~2 GB spare), at ~29.5 tok/s (estimated), with room for about 16,384 tokens of context.
Q2_K — it needs about 10 GB of the 12 GB available, downloads as roughly 7.9 GB, and runs at an estimated 29.5 tokens/sec with up to 16K 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