GreenBitAI/DeepSeek-R1-Distill-Qwen-32B-layer-mix-bpw-4.0-mlx

This quantized low-bit model GreenBitAI/DeepSeek-R1-Distill-Qwen-32B-layer-mix-bpw-4.0-mlx was converted to MLX format from GreenBitAI/DeepSeek-R1-Distill-Qwen-32B-layer-mix-bpw-4.0 using gbx-lm version 0.3.7. Refer to the original model card for more details on the model.

Use with mlx

pip install gbx-lm

from gbx_lm import load, generate

model, tokenizer = load("GreenBitAI/DeepSeek-R1-Distill-Qwen-32B-layer-mix-bpw-4.0-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)