---
title: Baichuan-M1-14B-Instruct-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Baichuan-M1-14B-Instruct-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Baichuan-M1-14B-Instruct-8bit.md"
repository: mlx-community/Baichuan-M1-14B-Instruct-8bit
last_updated: 2025-04-27
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - baichuan_m1
architectures:
  - BaichuanM1ForCausalLM
base_model:
  - baichuan-inc/Baichuan-M1-14B-Instruct
base_model_relation: quantized
parameters: 4.1B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 419
stars: 0
tags:
  - medical
  - mlx
---

# Baichuan-M1-14B-Instruct-8bit

> Baichuan-M1-14B-Instruct-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Baichuan-M1-14B-Instruct-8bit

mlx-community/Baichuan-M1-14B-Instruct-8bit 是 ModelScope 魔搭社区上的 4.1B 参数text-generation模型，基于 baichuan-inc/Baichuan-M1-14B-Instruct 构建。

- **Repository**: mlx-community/Baichuan-M1-14B-Instruct-8bit
- **Tasks**: text-generation
- **Parameters**: 4.1B
- **Base model**: baichuan-inc/Baichuan-M1-14B-Instruct
- **Tags**: medical, mlx
- **Downloads**: 419
- **Stars**: 0
- **Last updated**: 2025-04-27

Source: https://www.modelscope.cn/models/mlx-community/Baichuan-M1-14B-Instruct-8bit

---

# mlx-community/Baichuan-M1-14B-Instruct-8bit

This model [mlx-community/Baichuan-M1-14B-Instruct-8bit](https://huggingface.co/mlx-community/Baichuan-M1-14B-Instruct-8bit) was
converted to MLX format from [baichuan-inc/Baichuan-M1-14B-Instruct](https://huggingface.co/baichuan-inc/Baichuan-M1-14B-Instruct)
using mlx-lm version **0.23.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Baichuan-M1-14B-Instruct-8bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```