Gemma3-27B-it-vl-HERETIC-GLM4.7-2200x-cp515-q8-mlx

Brainwaves

Gemma-3-27b-it-HERETIC-Gemini-Deep-Reasoning
q8   0.596,0.748,0.881,0.779,0.458,0.819,0.751

Gemma3-27B-it-vl-HERETIC-GLM4.7-2200x-cp515
q8   0.566,0.737,0.876,0.745,0.420,0.805,0.759

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Gemma3-27B-it-vl-HERETIC-GLM4.7-2200x-cp515-q8-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, return_dict=False,
    )

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