---
license: apache-2.0
base_model: roslein/Qwen3-32B-abliterated
library_name: mlx
pipeline_tag: text-generation
tags:
- mlx
---

# litmudoc/Qwen3-32B-abliterated-MLX-Q8

This model [litmudoc/Qwen3-32B-abliterated-MLX-Q8](https://huggingface.co/litmudoc/Qwen3-32B-abliterated-MLX-Q8) was
converted to MLX format from [roslein/Qwen3-32B-abliterated](https://huggingface.co/roslein/Qwen3-32B-abliterated)
using mlx-lm version **0.24.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("litmudoc/Qwen3-32B-abliterated-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)
```