LLM EXPLORER 60,958 MODELS INDEXED

Gemma 4 26B A4B It Heretic Msq 2.6bit by mlx-community

By mlx-community · 539 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B It Heretic Msq 2.6bit is an open-source language model by mlx-community. Features: 26b LLM, VRAM: 10.2GB, License: apache-2.0, LLM Explorer Score: 0.25.

  4-bit   Abliterated   Ara Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Conversational   Decensored   Endpoints compatible   Gemma4   Heretic   Image-text-to-text   Mixed-precision   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit 

Gemma 4 26B A4B It Heretic Msq 2.6bit Parameters and Internals

LLM NameGemma 4 26B A4B It Heretic Msq 2.6bit
Repository 🤗https://huggingface.co/mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit 
Base Model(s)  Gemma 4 26B A4B It   google/gemma-4-26B-A4B-it
Model Size26b
Required VRAM10.2 GB
Updated2026-08-08
Maintainermlx-community
Model Typegemma4
Model Files  5.4 GB: 1-of-2   4.8 GB: 2-of-2
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4B It Heretic Msq 2.6bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 26B A4B It0K / 51.6 GB104059891007
Gemma 4 26B A4B0K / 51.6 GB624397370
Gemma 4 26B A4B It0K / 51.6 GB3215128
Gemma 4 26B A4B StyleTune V20K / 53.1 GB159849
Gemma 4 26B A4B0K / 51.6 GB336819
Gemma 4 26B A4b It Bf160K / 51.6 GB15173
Gemma 4 26B A4B NVFP40K / 18.8 GB1424962126
Gemma 4 26B A4B It NVFP40K / 16.9 GB15466321
Gemma 4 26B A4B It FP8 Dynamic0K / 28.6 GB113634938
...theon Reasoning 26B A4B 1.1 V20K / 53.1 GB26218
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit.