README.md

---
license: mit
library_name: mlx
tags:
- mlx
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
pipeline_tag: text-generation
---

# mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ

This model [mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ](https://huggingface.co/mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ) was
converted to MLX format from [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
using mlx-lm version **0.25.2**.

AWQ Parameters: --bits 4 --group-size 64 --embed-bits 4 --embed-group-size 32 --num-samples 256 --sequence-length 1024 --n-grid 50

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-AWQ")

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)
```