| library_name: transformers | |
| tags: | |
| - compression | |
| - expert-merging | |
| - moe | |
| - code | |
| - mlx | |
| - mlx-my-repo | |
| license: apache-2.0 | |
| base_model: bknyaz/Qwen3-Coder-Next-REAM | |
| # TomLucidor/Qwen3-Coder-Next-REAM-mlx-4Bit | |
| The Model [TomLucidor/Qwen3-Coder-Next-REAM-mlx-4Bit](https://huggingface.co/TomLucidor/Qwen3-Coder-Next-REAM-mlx-4Bit) was converted to MLX format from [bknyaz/Qwen3-Coder-Next-REAM](https://huggingface.co/bknyaz/Qwen3-Coder-Next-REAM) using mlx-lm version **0.29.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("TomLucidor/Qwen3-Coder-Next-REAM-mlx-4Bit") | |
| prompt="hello" | |
| if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: | |
| messages = [{"role": "user", "content": prompt}] | |
| prompt = tokenizer.apply_chat_template( | |
| messages, tokenize=False, add_generation_prompt=True | |
| ) | |
| response = generate(model, tokenizer, prompt=prompt, verbose=True) | |
| ``` | |