Can I Run Codestral on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?
Superseded model. Codestral has been superseded by Devstral. This page is kept for reference; the newer family is a better starting point.
View Devstral →
Written by Jakub Rusinowski · Last updated May 29, 2024
Yes
Yes — Codestral 22B 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 ~30.5 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q2_K · Estimated speed: ~30.5 tok/s
RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) — what it gives a model
| Usable memory for models | 12 GB |
| Memory bandwidth | 360 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
Codestral on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM): memory by quantization
| Quant | Memory needed | Fits 12 GB? | Max context | Est. speed | Download |
|---|
| F16 | 47.1 GB | ✗ No | — | — | 44.4 GB |
| Q8_0 | 26.3 GB | ✗ No | — | — | 23.6 GB |
| Q6_K | 20.9 GB | ✗ No | — | — | 18.2 GB |
| Q5_K_M | 18.4 GB | ✗ No | — | — | 15.7 GB |
| Q4_K_M | 16.1 GB | ✗ No | — | — | 13.4 GB |
| Q3_K_M | 12.1 GB | ✗ No | — | — | 9.5 GB |
| Q2_K | 10 GB | ✓ Yes | 16K | ~30.5 tok/s | 7.3 GB |
What to watch out for
- Q2_K is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 1 larger variant of Codestral does not fit and would need CPU offload or different hardware.
RTX 3060 12 GB desktop limitations
- The budget entry point to local AI: 12 GB runs 7–14B models well and nothing larger without offload.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 12 GB of VRAM on the NVIDIA GeForce RTX 3060 (12GB) at 360 GB/s.
- 32 GB of system RAM available for CPU offload when a model exceeds VRAM.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run Codestral on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?
Yes — Codestral 22B 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 ~30.5 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Codestral should I use on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?
Q2_K — it needs about 10 GB of the 12 GB available, downloads as roughly 7.3 GB, and runs at an estimated 30.5 tokens/sec with up to 16K of context.
What limits Codestral on RTX 3060 12 GB Desktop (12 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 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)
Codestral on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Codestral model page | Check your hardware