Qwen3-42B-A3B-Spock-Brutal-Recall-Instruct-qx86-hi-mlx

bf16     0.560,0.735,0.871,0.760,0.454,0.805,0.722
qx86-hi  0.556,0.730,0.872,0.759,0.446,0.808,0.732

This model Qwen3-42B-A3B-Spock-Brutal-Recall-Instruct-qx86-hi-mlx was converted to MLX format from DavidAU/Qwen3-42B-A3B-Spock-Brutal-Recall-Instruct using mlx-lm version 0.29.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-42B-A3B-Spock-Brutal-Recall-Instruct-qx86-hi-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)