Mixtral Models — Hardware Requirements
4 Mixtral models from Mistral AI and the community, from the smallest that runs in 19.8 GB of VRAM up to 140.6B parameters. Every row links to full quantization tables and GPU compatibility.
All Mixtral Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Mixtral 8x7B Instruct v0.1 | 46.7B | 20.4 GB | 33K | ||
| Mixtral 8x7B v0.1 | 46.7B | 19.8 GB | 33K | ||
| Mixtral 34Bx2 MoE 60B | 60.8B | 26.6 GB | 200K | ||
| Mixtral 8x22B v0.1 | 140.6B | 60.5 GB | 66K |
Frequently Asked Questions
- How much VRAM do I need to run a Mixtral model?
- The smallest Mixtral model, Mixtral 8x7B v0.1, runs from 19.8 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Mixtral models can I run on a 16 GB GPU?
- No Mixtral model currently fits in 16 GB of VRAM — the family starts at 19.8 GB.
- What is the most popular Mixtral model to run locally?
- Mixtral 8x7B Instruct v0.1 is the most downloaded Mixtral model in local-friendly quantized formats. It runs from 20.4 GB of VRAM.