Skip to content

JoaoZaokk

Gemma-3-12B-it-Heretic-W4A8

JoaoZaokk/Gemma-3-12B-it-Heretic-W4A8

Gemma-3-12B-it-Heretic-W4A8 is a machine learning model from JoaoZaokk. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for comfyui. The card lists the license as gemma.

4-bit weights with an 8-bit activation path, in ComfyUI's native per-layer quantization format. 21.93 GiB → 7.53 GiB, 2.91x lighter, and on the path ComfyUI takes by default it costs no extra time at all.

Downloads · 30 days

0

Access

Public

Updated Sep 25, 2026

Repo size

37.1 GB

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors37.1 GB · 100%

At a glance

Library
comfyui
License
gemma
Access
Public
Created
Sep 12, 2026
Updated
Sep 25, 2026
SHA
186a2d06

Base models

Library
comfyui
License
gemma
Created
Sep 12, 2026
Updated
Sep 25, 2026