Mistral AI · open-weights model
Mistral-Small-24B-Instruct-2501
Mistral-Small-24B-Instruct-2501 is a 23.6B-parameter model by Mistral AI. Its smallest quant (Q4_K_M) needs at least 16.2GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 21 of the 50 machines we track.
- Parameters
- 23.6B
- Layers
- 40
- Max context
- 32K
- Attention
- GQA
- License
- apache-2.0
Config from mistralai/Mistral-Small-24B-Instruct-2501
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 25.1 GB | 26.9 GB |
| Q6_K | 19.4 GB | 21.2 GB |
| Q5_K_M | 16.8 GB | 18.6 GB |
| Q4_K_M | 14.3 GB | 16.2 GB |
What runs Mistral-Small-24B-Instruct-2501
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.