LLM EXPLORER 60,828 MODELS INDEXED

Gemma 4 26B A4B It Qat Heretic Ega by xdavxd

By xdavxd · 55 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B It Qat Heretic Ega is an open-source language model by xdavxd. Features: 26b LLM, VRAM: 51.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

  Abliterated Base model:finetune:google/gem... Base model:google/gemma-4-26b-...   Biprojection   Conversational   Ega   Endpoints compatible   Gemma4   Gemma4-26b-a4b-it   Heretic   Image-text-to-text   Q4   Q4 0   Qat   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vllm
Model Card on HF 🤗: https://huggingface.co/xdavxd/gemma-4-26B-A4B-it-qat-heretic-ega 

Gemma 4 26B A4B It Qat Heretic Ega Parameters and Internals

LLM NameGemma 4 26B A4B It Qat Heretic Ega
Repository 🤗https://huggingface.co/xdavxd/gemma-4-26B-A4B-it-qat-heretic-ega 
Base Model(s)  ...6B A4B It Qat Q4 0 Unquantized   google/gemma-4-26B-A4B-it-qat-q4_0-unquantized
Model Size26b
Required VRAM51.6 GB
Updated2026-09-10
Maintainerxdavxd
Model Typegemma4
Model Files  49.3 GB: 1-of-2   2.3 GB: 2-of-2
Quantization Typeq4|q4_0
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.16.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4B It Qat Heretic Ega

Best Alternatives
Context / RAM
Downloads
Likes
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB3369650
Gemma 4 26B A4b It 4bit0K / 15.4 GB2754379
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB34873
Gemma 4 26B A4b It 8bit0K / 27.9 GB291714
Gemma 4 26B A4b It UD MLX 4bit0K / 16.2 GB152734
Gemma 4 26B A4b It MLX 8bit0K / 27.9 GB93616
...at Q4 0 Unquantized Heretic Ja0K / 51.6 GB341
Gemma 4 26B A4b 4bit0K / 15.6 GB48819
Gemma 4 26B A4b It 6bit0K / 21.7 GB6117
Gemma 4 26B A4b It UD MLX 3bit0K / 13.1 GB4558
Note: green Score (e.g. "73.2") means that the model is better than xdavxd/gemma-4-26B-A4B-it-qat-heretic-ega.