---
title: Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf.md"
repository: AI-ModelScope/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf
last_updated: 2024-03-05
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mixtral
architectures:
  - MixtralForCausalLM
parameters: 6.5B
tensor_type:
  - F16
  - I16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 5012
stars: 0
---

# Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf

> Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf - AI-ModelScope 在 ModelScope 开源的模型。Official AQLM quantization of mistralai/Mixtral-8x7B-Instruct-v0.1.

AI-ModelScope/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf 是 ModelScope 魔搭社区上的 6.5B 参数text-generation模型，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: AI-ModelScope/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf
- **Tasks**: text-generation
- **Parameters**: 6.5B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 5012
- **Stars**: 0
- **Last updated**: 2024-03-05

Source: https://www.modelscope.cn/models/AI-ModelScope/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf

---

Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of `mistralai/Mixtral-8x7B-Instruct-v0.1`.

For this quantization, we used 1 codebook of 16 bits.

Selected evaluation results for this model: 

| Model      | AQLM scheme | WinoGrande | PiQA | HellaSwag | ArcE | ArcC | Model size, Gb | Hub link |
|------|------|------|-------|-------|-------|------|------|------|
| Mixtral-8x7B-Instruct-v0.1 (THIS)| 1x16 | 0.7593 |0.8043 | 0.6179 | 0.7768 | 0.4793 | 12.6 | [Link](https://huggingface.co/BlackSamorez/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf)|

To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the [official GitHub repo](https://github.com/Vahe1994/AQLM).