qwen3.5-4B-super-coder MLX 4-bit
MLX 4-bit build of jica98/qwen3.5-4B-super-coder.
The source repo only ships the LoRA adapter and GGUF exports, so this was built by:
- Loading
unsloth/Qwen3.5-4B - Merging the
jica98/qwen3.5-4B-super-coderLoRA adapter withQwen3_5ForConditionalGeneration - Converting the merged Hugging Face model to MLX
- Quantizing to 4-bit with
mlx-lmNo additional training was done.
Use
pip install -U mlx-lm
mlx_lm.generate \
--model snsnc/qwen3.5-4B-super-coder-MLX-4bit \
--max-tokens 2048 \
--temp 0.7 \
--top-p 0.8 \
--top-k 20 \
--chat-template-config '{"enable_thinking":false}' \
--prompt "Write only executable Python code. Implement an async token-bucket rate limiter."
Thinking is enabled by the upstream chat template unless explicitly disabled.