Downloads · 30 days
10
1% of all-time downloads
TheCluster/amoral-gemma-3-12B-v2-mlx-8bit
amoral-gemma-3-12B-v2-mlx-8bit is a image-text-to-text model from TheCluster. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
Specialized uncensored variant of Google's Gemma 3 12B optimized for amoral information retrieval systems. Designed to bypass conventional alignment patterns that introduce response bias through excessive moralization.
Downloads · 30 days
10
1% of all-time downloads
All-time downloads
710
Public
Repo size
14.5 GB
Likes
1
Public
Click a slice to open those files.
.safetensors14.4 GB · 100%
From the Hugging Face model README
Specialized uncensored variant of Google's Gemma 3 12B optimized for amoral information retrieval systems. Designed to bypass conventional alignment patterns that introduce response bias through excessive moralization.
Key Modifications:
Recommended Use Cases:
This model was converted to MLX format from soob3123/amoral-gemma3-12B-v2 using mlx-vlm version 0.1.22.
Refer to the original model card and amoral model for more details on the model.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model TheCluster/amoral-gemma-3-12B-v2-mlx-8bit --max-tokens 512 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>