leonsarmiento/Qwen3-8B-Claude-4.5-Opus-High-Reasoning-Distill-8bit-mlx

This model leonsarmiento/Qwen3-8B-Claude-4.5-Opus-High-Reasoning-Distill-8bit-mlx was converted to MLX format from TeichAI/Qwen3-8B-Claude-4.5-Opus-High-Reasoning-Distill using mlx-lm version 0.28.3.

Recommended Parameters:

Temperature: 0.6 Top K: 20 Repeat penalty: OFF Min P sampling: 0.0 Top P sampling: 0.95

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("leonsarmiento/Qwen3-8B-Claude-4.5-Opus-High-Reasoning-Distill-8bit-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)