LLM EXPLORER 57,252 MODELS INDEXED

Gemma 4 26B A4B It FP8 Dynamic by RedHatAI

By RedHatAI · 1136349 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B It FP8 Dynamic is an open-source language model by RedHatAI. Features: 26b LLM, VRAM: 28.6GB, License: apache-2.0, LLM Explorer Score: 0.36.

Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Compressed-tensors   Conversational   Endpoints compatible   Fp8   Gemma4   Image-text-to-text   Llm-compressor   Region:us   Safetensors   Vllm
Model Card on HF 🤗: https://huggingface.co/RedHatAI/gemma-4-26B-A4B-it-FP8-dynamic 

Gemma 4 26B A4B It FP8 Dynamic Parameters and Internals

LLM NameGemma 4 26B A4B It FP8 Dynamic
Repository 🤗https://huggingface.co/RedHatAI/gemma-4-26B-A4B-it-FP8-dynamic 
Base Model(s)  Gemma 4 26B A4B It   google/gemma-4-26B-A4B-it
Model Size26b
Required VRAM28.6 GB
Updated2026-08-09
MaintainerRedHatAI
Model Typegemma4
Model Files  28.6 GB
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4B It FP8 Dynamic

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 26B A4B It0K / 51.6 GB104059891007
Gemma 4 26B A4B StyleTune V20K / 53.1 GB159849
Gemma 4 26B A4B It0K / 51.6 GB4301024
Gemma 4 26B A4b It Bf160K / 51.6 GB15173
Gemma 4 26B A4B NVFP40K / 18.8 GB1424962126
Gemma 4 26B A4B0K / 51.6 GB624397370
Gemma 4 26B A4B It NVFP40K / 16.4 GB74281939
G4 Dark Soul 26B A4B0K / 51.6 GB90617
Gemma 4 26B A4B NVFP40K / 18.8 GB5061
G4 Midnight Macaw 26B A4B0K / 51.6 GB869
Note: green Score (e.g. "73.2") means that the model is better than RedHatAI/gemma-4-26B-A4B-it-FP8-dynamic.