LLM EXPLORER 62,076 MODELS INDEXED

Gemma 4 26B A4B by google

By google · 624397 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B is an open-source language model by google. Features: 26b LLM, VRAM: 51.6GB, License: apache-2.0, LLM Explorer Score: 0.52, ELO: 1438.

  Arxiv:2607.02770   Endpoints compatible   Gemma4   Image-text-to-text   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/google/gemma-4-26B-A4B 

Gemma 4 26B A4B Benchmarks

LMSys ELO 1438 vs 1272 (so35) 13.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 4 26B A4B Parameters and Internals

LLM NameGemma 4 26B A4B
Repository 🤗https://huggingface.co/google/gemma-4-26B-A4B 
Model Size26b
Required VRAM51.6 GB
Updated2026-08-09
Maintainergoogle
Model Typegemma4
Model Files  49.9 GB: 1-of-2   1.7 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

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 26B A4B It0K / 51.6 GB104059891007
Gemma 4 26B A4B It0K / 51.6 GB2854129
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
WaifuGemma4 26B A4b V10K / 51.6 GB85010
Gemma 4 26B A4B It NVFP40K / 16.4 GB74281939
Note: green Score (e.g. "73.2") means that the model is better than google/gemma-4-26B-A4B.