metadata
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- mlx
base_model: Qwen/Qwen3-Coder-480B-A35B-Instruct
cs2764/Qwen3-Coder-480B-A35B-Instruct-mlx-6Bit
The Model cs2764/Qwen3-Coder-480B-A35B-Instruct-mlx-6Bit was converted to MLX format from Qwen/Qwen3-Coder-480B-A35B-Instruct using mlx-lm version 0.28.1.
Quantization Details
This model was converted with the following quantization settings:
- Quantization Strategy: 6-bit quantization
- Average bits per weight: 6.500
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("cs2764/Qwen3-Coder-480B-A35B-Instruct-mlx-6Bit")
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)