Can I Run Mistral Small 3 (24B) on NVIDIA GeForce RTX 3060 (12GB)?
作者： Jakub Rusinowski · 最后更新： 2026年9月19日
Not at Q4_K_M — that needs 14.5 GB and the NVIDIA GeForce RTX 3060 (12GB) has 12 GB. Drop to Q2_K and it fits in 10.6 GB, with up to 8K of context.
Get a personalized upgrade path →
The numbers
| Model | Mistral Small 3 (24B) |
| Parameters | 24B |
| Quantization | Q4_K_M |
| VRAM needed | 14.5 GB |
| NVIDIA GeForce RTX 3060 (12GB) VRAM | 12 GB |
| Verdict | Runs at a lower quant |
| Fits at | Q2_K (10.6 GB) |
| Max context | 8K |
Mistral Small 3 (24B) on the NVIDIA GeForce RTX 3060 (12GB): VRAM by quantization
| Quant | VRAM needed | Fits 12 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 49.7 GB | ✗ No | — | — |
| Q8_0 | 27.2 GB | ✗ No | — | Build for this |
| Q6_K | 21.4 GB | ✗ No | — | — |
| Q5_K_M | 18.7 GB | ✗ No | — | — |
| Q4_K_M | 16.2 GB | ✗ No | — | Build for this |
| Q3_K_M | 12 GB | ✓ Yes | 4K | — |
| Q2_K | 9.6 GB | ✓ Yes | 8K | — |
Assumes a 4K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 12 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 3060 (12GB): 8K 17.2 GB ✗ · 32K 22.8 GB ✗. Past 8K it no longer fits 12 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Quantize to Q2_K. That is the cheapest fix — it costs some quality but no money.
No compatible GPU? Mistral Small 3 (24B) on 24 GB of system RAM, CPU only: runs comfortably.
Running Mistral Small 3 (24B) on this card:
Mistral Small 3 (24B) needs ~14 GB but this GPU has 12 GB. Rent a RTX 4090 (24 GB)-class GPU by the hour instead of buying one:
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other Mistral Family sizes on the NVIDIA GeForce RTX 3060 (12GB)
- Mistral NeMo 12B — runs (7.2 GB)
Mistral Small 3 (24B) on nearby hardware
- Intel Arc B570 (10 GB) — does not fit
- NVIDIA GeForce RTX 5080 (16 GB) — runs at a lower quant
All Mistral Family sizes on the NVIDIA GeForce RTX 3060 (12GB) | Mistral Small 3 (24B) model page | NVIDIA GeForce RTX 3060 (12GB) GPU page | Check your hardware