Downloads · 30 days
108
13% of all-time downloads
mlx-community/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-4.6bit-msq
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-4.6bit-msq is a image-text-to-text model from mlx-community. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Mixed-precision MLX quantization of DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Sili…
Downloads · 30 days
108
13% of all-time downloads
All-time downloads
843
Public
Parameters
31.2B
20.2 GB on disk
Likes
4
Public
Click a slice to open those files.
.safetensors20.2 GB · 100%
How the weights are stored.
U324.3B · 74%
From the Hugging Face model README
Mixed-precision MLX quantization of DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.