---
library_name: mlx
license: apache-2.0
pipeline_tag: text-generation
base_model: BennyDaBall/qwen3-4b-Z-Image-Engineer-V2-6bit-MLX
tags:
- mlx
- qwen3
- 6-bit
- z-image-turbo
- prompt-engineering
- prompt-enhancer
- apple-silicon
---

# tokenfires/qwen3-4b-Z-Image-Engineer-V2-6bit-MLX

Mirror of [BennyDaBall/qwen3-4b-Z-Image-Engineer-V2-6bit-MLX](https://huggingface.co/BennyDaBall/qwen3-4b-Z-Image-Engineer-V2-6bit-MLX),
a Qwen3-4B fine-tune that expands short prompts into detailed Z-Image-Turbo prompts. Kept under `tokenfires` so a load-bearing local model can be restored if the upstream repo changes or disappears.

Quantization: affine, 6 bits, group size 64. The weights are unchanged from upstream. See the upstream card for usage notes and the recommended system prompt (`system_prompt.json` is included here).

## Use with LM Studio

Search for `tokenfires/qwen3-4b-Z-Image-Engineer-V2-6bit-MLX` in the LM Studio model downloader, or open this page and choose **Use this model → LM Studio**.

## Use with mlx-lm

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

```python
from mlx_lm import load, generate

model, tokenizer = load("tokenfires/qwen3-4b-Z-Image-Engineer-V2-6bit-MLX")

messages = [{"role": "user", "content": "a lighthouse at dusk"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```