Modelpublic

porschefreak/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx-mlx-4Bit

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

1likes158downloads

Model Card

porschefreak/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx-mlx-4Bit

The Model porschefreak/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx-mlx-4Bit was converted to MLX format from nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx using mlx-lm version 0.31.2.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("porschefreak/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx-mlx-4Bit")

prompt="hello"

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

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