Mistral AI
Mixtral 8x7B Instruct
Mixture-of-experts model with 8 experts of 7B each. Excellent quality at moderate resource requirements.
46.7B parametersmixtralapache-2.032K context28GB - 52GB VRAM
Check Your Hardware
See which quantizations of Mixtral 8x7B Instruct your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| Q4_K_M | 4.5 | 26.4 GB | 28 GB | 32 GB | 85% |
| Q5_K_M | 5.5 | 32.2 GB | 34 GB | 40 GB | 90% |
| Q8_0 | 8 | 49.6 GB | 52 GB | 56 GB | 98% |
Frequently Asked Questions
How much VRAM do I need to run Mixtral 8x7B Instruct?
Mixtral 8x7B Instruct requires 28GB VRAM minimum with Q4_K_M quantization. For full precision, you need 52GB VRAM.
What is the best quantization for Mixtral 8x7B Instruct?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.