Downloads · 30 days
40
3% of all-time downloads
CallMcMargin/gemma-3-12b-it-heretic-mlx-bf16-affine-qgroup32-q8
gemma-3-12b-it-heretic-mlx-bf16-affine-qgroup32-q8 is a text generation model from CallMcMargin. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as gemma.
This model CallMcMargin/gemma-3-12b-it-heretic-mlx-bf16-affine-qgroup32-q8 was converted to MLX format from p-e-w/gemma-3-12b-it-heretic using mlx-lm version 0.28.4.
Downloads · 30 days
40
3% of all-time downloads
All-time downloads
1.2K
Public
Parameters
11.8B
13.3 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors13.2 GB · 100%
How the weights are stored.
U3211.8B · 100%
From the Hugging Face model README
This model CallMcMargin/gemma-3-12b-it-heretic-mlx-bf16-affine-qgroup32-q8 was converted to MLX format from p-e-w/gemma-3-12b-it-heretic using mlx-lm version 0.28.4.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("CallMcMargin/gemma-3-12b-it-heretic-mlx-bf16-affine-qgroup32-q8")
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)