GraySoft
Model Comparison

davidau/openai-gpt-oss-20b-heretic-uncensored-neo-imatrix-ggufvsmudler/gemma-4-26b-a4b-it-heretic-apex-gguf

Side-by-side comparison of davidau/openai-gpt-oss-20b-heretic-uncensored-neo-imatrix-gguf and mudler/gemma-4-26b-a4b-it-heretic-apex-gguf: downloads, license, context length, tasks, and benchmarks.

davidau/openai-gpt-oss-20b-heretic-uncensored-neo-imatrix-gguf

DavidAU · text-generation

Specialized uncensored quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S. See settings and special instructions for using UNCENSORED (refusals removed // "nanny be gone") models below. "HERETIC" method results in a model devoid of refusals, and without brain da…

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

davidau/openai-gpt-oss-20b-heretic-uncensored-neo-imatrix-ggufmudler/gemma-4-26b-a4b-it-heretic-apex-gguf
AuthorDavidAUmudler
Pipeline Tasktext-generation
Library
Downloads24,33318,849
Likes12622
LicenseUnknownUnknown
Context Length
Created2025-11-172026-04-05
Last Modified2025-11-302026-04-05
Tags
ggufgpt_ossgpt-ossopenaimxfp4programmingcode generationcodecodingcoder
ggufquantizedapexmoemixture-of-expertsgemma4vlmvisionbase_model:coder3101/gemma-4-26B-A4B-it-hereticbase_model:quantized:coder3101/gemma-4-26B-A4B-it-heretic

View full details: davidau/openai-gpt-oss-20b-heretic-uncensored-neo-imatrix-gguf · mudler/gemma-4-26b-a4b-it-heretic-apex-gguf