---
base_model: sm54/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B
library_name: mlx
tags:
- mergekit
- merge
- mlx
pipeline_tag: text-generation
---

# litmudoc/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-MLX-Q8

This model [litmudoc/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-MLX-Q8](https://huggingface.co/litmudoc/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-MLX-Q8) was
converted to MLX format from [sm54/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B](https://huggingface.co/sm54/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B)
using mlx-lm version **0.22.2**.

## GGUF conversion MLX
```bash
pip install mlx mlx-lm
mlx_lm.convert --hf-path sm54/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B -q --q-bits 8 --upload-repo litmudoc/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-MLX-Q8
```

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("litmudoc/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-MLX-Q8")

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)
```