GraySoft
Model Comparison

jiunsong/supergemma4-26b-uncensored-gguf-v2vsmudler/gemma-4-26b-a4b-it-heretic-apex-gguf

Side-by-side comparison of jiunsong/supergemma4-26b-uncensored-gguf-v2 and mudler/gemma-4-26b-a4b-it-heretic-apex-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:

mudler/gemma-4-26b-a4b-it-heretic-apex-gguf

mudler · —

**APEX (Adaptive Precision for EXpert Models)** quantizations of gemma-4-26B-A4B-it-heretic — an **abliterated (uncensored)** version of Gemma 4, created with the Heretic tool (v1.2.0) using Arbitrary-Rank Ablation (ARA) on layers 10-30 to reduce refusals while preserving capabi…

Side-by-side Specifications

jiunsong/supergemma4-26b-uncensored-gguf-v2mudler/gemma-4-26b-a4b-it-heretic-apex-gguf
AuthorJiunsongmudler
Pipeline Tasktext-generation
Library
Downloads42,46818,849
Likes33622
LicenseUnknownUnknown
Context Length
Created2026-04-112026-04-05
Last Modified2026-04-122026-04-05
Tags
ggufgemma4uncensoredfastllama.cppapple-siliconconversationalkoreancodingtool-use
ggufquantizedapexmoemixture-of-expertsgemma4vlmvisionbase_model:coder3101/gemma-4-26B-A4B-it-hereticbase_model:quantized:coder3101/gemma-4-26B-A4B-it-heretic

View full details: jiunsong/supergemma4-26b-uncensored-gguf-v2 · mudler/gemma-4-26b-a4b-it-heretic-apex-gguf