by NexVeridian
Open source · 430k downloads · 2 likes
The Qwen3 Coder Next 8bit model is an optimized version of Qwen3 Coder Next, specifically designed for software development and programming assistance. It excels in generating, correcting, and explaining code while providing a deep understanding of modern programming languages and frameworks. Its capabilities include autocompletion, automatic documentation, and technical problem-solving, making it a valuable tool for developers and technical teams. This model stands out for its efficiency thanks to 8-bit quantization, enabling faster execution and reduced resource consumption without compromising response quality. Ideal for environments where performance and precision are critical, it adapts seamlessly to both individual projects and collaborative workflows.
This model NexVeridian/Qwen3-Coder-Next-8bit was converted to MLX format from Qwen/Qwen3-Coder-Next using mlx-lm version 0.30.8.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("NexVeridian/Qwen3-Coder-Next-8bit")
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)