README.md

---
language: en
license: apache-2.0
library_name: mlx
pipeline_tag: text-generation
base_model: Jackrong/Qwopus3.5-9B-Coder
tags:
- mlx
- qwen3_5
- code
- agent
- tool-use
- text-generation
---

# Qwopus3.5-9B-Coder-MLX

MLX conversion of [`Jackrong/Qwopus3.5-9B-Coder`](https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder) for Apple Silicon.

Original upstream weights, converted to MLX format only. No additional fine-tuning or architecture changes.

## Use with mlx-lm

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

```python
from mlx_lm import load, generate

model, tokenizer = load("snsnc/Qwopus3.5-9B-Coder-MLX")

prompt = "Write a short Python function that returns the factorial of a number."

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
print(response)
```

## Use with mlx-serve

```bash
pip install -U mlx-serve
```

```bash
mlx-serve \
  --model hf://snsnc/Qwopus3.5-9B-Coder-MLX \
  --serve \
  --host 0.0.0.0 \
  --port 11234
```

## Upstream

- Original model: [`Jackrong/Qwopus3.5-9B-Coder`](https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder)