GraySoft
Download guIDE →
Model Comparison

microsoft/bitnet-b1.58-2b-4t-ggufvsmudler/gemma-4-26b-a4b-it-heretic-apex-gguf

Side-by-side comparison of microsoft/bitnet-b1.58-2b-4t-gguf and mudler/gemma-4-26b-a4b-it-heretic-apex-gguf: downloads, license, context length, tasks, and benchmarks.

microsoft/bitnet-b1.58-2b-4t-gguf

microsoft · text-generation

This repository contains the weights for **BitNet b1.58 2B4T**, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale, developed by Microsoft Research. Trained on a corpus of 4 trillion tokens, this model demonstrates that native 1-bit L…

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

microsoft/bitnet-b1.58-2b-4t-ggufmudler/gemma-4-26b-a4b-it-heretic-apex-gguf
Authormicrosoftmudler
Pipeline Tasktext-generation—
Librarytransformers—
Downloads36,03018,849
Likes26622
LicenseUnknownUnknown
Context Length——
Created2025-04-152026-04-05
Last Modified2025-12-172026-04-05
Tags
transformersggufchatbitnettext-generationlarge-language-modelenarxiv:2504.12285license:mitendpoints_compatible
ggufquantizedapexmoemixture-of-expertsgemma4vlmvisionbase_model:coder3101/gemma-4-26B-A4B-it-hereticbase_model:quantized:coder3101/gemma-4-26B-A4B-it-heretic

View full details: microsoft/bitnet-b1.58-2b-4t-gguf · mudler/gemma-4-26b-a4b-it-heretic-apex-gguf