Mixtral models
1 Mixtral model from Mistral AI on Hugging Face, from 46.7B to 46.7B parameters, published by Mistral AI in BF16, with a 32K-token context. The smallest official model, Mixtral-8x7B-Instruct-v0.1, needs about 104 GB of VRAM at its published precision; the cheapest live fit is AMD MI300X at $2.63/hr.
Part of the Mistral series · Previous generation: Mistral 7B · Next generation: Mistral Small
Pick a size
One row per official Mixtral size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Mixtral-8x7B-Instruct-v0.1 | 46.7B | 104 GB | 52.2 GB | 26.1 GB | AMD MI300X | $2.63/hr | 4.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Mixtral-8x7B-Instruct-v0.1 | 46.7B | BF16 | 104 GB | AMD MI300X | $2.63/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. 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
- Voxtral (1 models)
- Mistral 7B (7 models)
- Mistral Small (3 models)
- mistralai (1 models)