This model NexVeridian/Qwen3-Coder-Next-6bit was converted to MLX format from Qwen/Qwen3-Coder-Next using mlx-lm version 0.31.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("NexVeridian/Qwen3-Coder-Next-6bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
model-00007-of-00013.safetensors 5.4 GBmodel-00008-of-00013.safetensors 5.4 GBmodel-00011-of-00013.safetensors 5.4 GBmodel-00006-of-00013.safetensors 5.4 GBmodel-00004-of-00013.safetensors 5.4 GBmodel-00010-of-00013.safetensors 5.4 GBmodel-00009-of-00013.safetensors 5.4 GBmodel-00012-of-00013.safetensors 5.4 GBmodel-00005-of-00013.safetensors 5.4 GBmodel-00003-of-00013.safetensors 5.4 GBmodel-00002-of-00013.safetensors 5.4 GBmodel-00001-of-00013.safetensors 5.2 GBmodel-00013-of-00013.safetensors 692 MB有文件？提交种子。
提交种子