---
license: mit
train: false
inference: true
pipeline_tag: text-generation
base_model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1
tags:
- mlx
---

# AlfRjw/DeepSeek-R1-ReDistill-Llama3-8B-v1.1-Q3-mlx

The Model [AlfRjw/DeepSeek-R1-ReDistill-Llama3-8B-v1.1-Q3-mlx](https://huggingface.co/AlfRjw/DeepSeek-R1-ReDistill-Llama3-8B-v1.1-Q3-mlx) was converted to MLX format from [mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1](https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1) 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("AlfRjw/DeepSeek-R1-ReDistill-Llama3-8B-v1.1-Q3-mlx")

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)
```