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: 1. Loading unsloth/Qwen3.5-4B 2. Merging the jica98/qwen3.5-4B-super-coder LoRA adapter with Qwen35ForConditionalGeneration 3. Converting the merged Hugging Face model to MLX 4. Quantizing to 4-bit with mlx-lm` No additional training was done. bash pip install -U mlx-lm mlxlm.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.
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: snsnc
Теги: mlx, qwen3_5, mlx-lm, code, 4-bit, conversational
Лайков: 3 | Загрузок: 584
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
