Mistral AI · open-weights model
Mistral-Nemo-Instruct-2407
Mistral-Nemo-Instruct-2407 is a 12.3B-parameter model by Mistral AI. Its smallest quant (Q4_K_M) needs at least 9.3GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 45 of the 50 machines we track.
- Parameters
- 12.3B
- Layers
- 40
- Max context
- 128K
- Attention
- GQA
- License
- apache-2.0
Config from mistralai/Mistral-Nemo-Instruct-2407
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 13.0 GB | 14.9 GB |
| Q6_K | 10.1 GB | 11.9 GB |
| Q5_K_M | 8.7 GB | 10.6 GB |
| Q4_K_M | 7.5 GB | 9.3 GB |
What runs Mistral-Nemo-Instruct-2407
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.