README.md

---
base_model: burtenshaw/Qwen3-30B-A3B-python-coder
datasets: burtenshaw/tulu-3-sft-personas-code-no-prompt
library_name: mlx
model_name: Qwen3-30B-A3B-python-coder
tags:
- generated_from_trainer
- trl
- sft
- mlx
licence: license
pipeline_tag: text-generation
---

# jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx

This model [jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx](https://huggingface.co/jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx) was
converted to MLX format from [burtenshaw/Qwen3-30B-A3B-python-coder](https://huggingface.co/burtenshaw/Qwen3-30B-A3B-python-coder)
using mlx-lm version **0.24.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx")

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)
```