GraySoft
Model Comparison

jiunsong/supergemma4-26b-uncensored-gguf-v2vsllmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf

Side-by-side comparison of jiunsong/supergemma4-26b-uncensored-gguf-v2 and llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf: downloads, license, context length, tasks, and benchmarks.

jiunsong/supergemma4-26b-uncensored-gguf-v2

Jiunsong · text-generation

The fast, uncensored llama.cpp build of the strongest SuperGemma text line. This release is for people who want three things together:

llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf

llmfan46 · image-text-to-text

GGUF quantizations of llmfan46/gemma-3-12b-it-ultra-uncensored-heretic. # This is a decensored version of google/gemma-3-12b-it, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method

Side-by-side Specifications

jiunsong/supergemma4-26b-uncensored-gguf-v2llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf
AuthorJiunsongllmfan46
Pipeline Tasktext-generationimage-text-to-text
Librarytransformers
Downloads42,46824,684
Likes33617
LicenseUnknownUnknown
Context Length
Created2026-04-112026-03-10
Last Modified2026-04-122026-03-27
Tags
ggufgemma4uncensoredfastllama.cppapple-siliconconversationalkoreancodingtool-use
transformersggufhereticuncensoreddecensoredabliteratedimage-text-to-textarxiv:1905.07830arxiv:1905.10044arxiv:1911.11641

View full details: jiunsong/supergemma4-26b-uncensored-gguf-v2 · llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf