---
tags:
- fp8
- vllm
---

# Mixtral-8x22B-Instruct-v0.1-FP8

## Model Overview
Mixtral-8x22B-Instruct-v0.1 quantized to FP8 weights and activations using per-tensor quantization, ready for inference with vLLM >= 0.5.0.

## Usage and Creation
Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py).

## Evaluation

### Open LLM Leaderboard evaluation scores
|                      | Mixtral-8x22B-Instruct-v0.1 | Mixtral-8x22B-Instruct-v0.1-FP8<br>(this model) |
| :------------------: | :----------------------: | :------------------------------------------------: |
| arc-c<br>25-shot     | 72.70                    | 69.19                                              |
| hellaswag<br>10-shot | 89.08                    | 82.49                                              |
| mmlu<br>5-shot       | 77.77                    | 70.61                                              |
| truthfulqa<br>0-shot | 68.14                    | 65.73                                              |
| winogrande<br>5-shot | 85.16                    | 82.63                                              |
| gsm8k<br>5-shot      | 82.03                    | 76.57                                              |
| **Average<br>Accuracy**  | **79.15**                    |              **74.53**                                     |
| **Recovery**             | **100%**                     |              **94.17%**                                     |