---
title: FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit.md"
repository: mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit
last_updated: 2026-05-08
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model_relation: quantized
parameters: 4.1B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 849
stars: 0
tags:
  - mlx
---

# FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit

> FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit

- **Repository**: mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit
- **Parameters**: 4.1B
- **Tags**: mlx
- **Downloads**: 849
- **Stars**: 0
- **Last updated**: 2026-05-08

Source: https://www.modelscope.cn/models/mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit

---

# mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit

The Model [mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit](https://huggingface.co/mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit) was converted to MLX format from [FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview) using mlx-lm version **0.20.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit")

prompt="hello"

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

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