Qwen3-21B-QiMing-V1.0-TOTAL-RECALL-q4-mlx

This model Qwen3-21B-QiMing-V1.0-TOTAL-RECALL-q4-mlx was converted to MLX format from DavidAU/Qwen3-21B-QiMing-V1.0-TOTAL-RECALL using mlx-lm version 0.26.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-21B-QiMing-V1.0-TOTAL-RECALL-q4-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)