GraySoft
Model Comparison

mudler/gemma-4-26b-a4b-it-heretic-apex-ggufvsteichai/devstral-small-2505-deepseek-v3.2-speciale-distill-gguf

Side-by-side comparison of mudler/gemma-4-26b-a4b-it-heretic-apex-gguf and teichai/devstral-small-2505-deepseek-v3.2-speciale-distill-gguf: downloads, license, context length, tasks, and benchmarks.

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…

teichai/devstral-small-2505-deepseek-v3.2-speciale-distill-gguf

TeichAI · —

This model was trained on a non-reasoning (reasoning traces were removed) dataset of **DeepSeek v3.2 Speciale**. ---

Side-by-side Specifications

mudler/gemma-4-26b-a4b-it-heretic-apex-ggufteichai/devstral-small-2505-deepseek-v3.2-speciale-distill-gguf
AuthormudlerTeichAI
Pipeline Task
Library
Downloads18,84922,100
Likes2211
LicenseUnknownUnknown
Context Length
Created2026-04-052026-02-04
Last Modified2026-04-052026-02-04
Tags
ggufquantizedapexmoemixture-of-expertsgemma4vlmvisionbase_model:coder3101/gemma-4-26B-A4B-it-hereticbase_model:quantized:coder3101/gemma-4-26B-A4B-it-heretic
ggufllama.cppunslothendataset:TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3kdataset:TeichAI/deepseek-v3.2-speciale-1000xdataset:TeichAI/deepseek-v3.2-speciale-openr1-math-3kbase_model:TeichAI/Devstral-Small-2505-Deepseek-V3.2-Speciale-Distillbase_model:quantized:TeichAI/Devstral-Small-2505-Deepseek-V3.2-Speciale-Distillendpoints_compatible

View full details: mudler/gemma-4-26b-a4b-it-heretic-apex-gguf · teichai/devstral-small-2505-deepseek-v3.2-speciale-distill-gguf