Voxtral models
1 Voxtral model on Hugging Face, from 4.4B to 4.4B parameters. The cheapest way to run Voxtral-Mini-4B-Realtime-2602 is $0.110/hr.
Voxtral models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Voxtral-Mini-4B-Realtime-2602 | 4.4B | BF16 | 9.9 GB | RTX 3060 | $0.110/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from Mistral AI
- Mistral 7B (8 models)
- Mistral Small (4 models)
