Will this model run on your hardware?
Can I run Mistral: Voxtral Small 24B 2507 locally?
- 24B parameters
- context up to 128K
- licence: apache-2.0
- Weights: mistralai/Voxtral-Small-24B-2507 · GGUF: handy-computer/Voxtral-Small-24B-2507-gguf
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 25.8 GB |
| Q6_K | 19.9 GB |
| Q5_K_M | 17.1 GB |
| Q4_K_M | 14.3 GB |
Run it locally
ollama run hf.co/handy-computer/Voxtral-Small-24B-2507-gguf:Q4_K_M
llama serve -hf handy-computer/Voxtral-Small-24B-2507-gguf:Q4_K_M