LLM EXPLORER 62,076 MODELS INDEXED

Orion 26B A4B V1.1 FP8 Dynamic by bandageshi

By bandageshi · 18 downloads
HF Repo ↗ Copy URL

Orion 26B A4B V1.1 FP8 Dynamic is an open-source language model by bandageshi. Features: 26b LLM, VRAM: 27.1GB, License: apache-2.0, LLM Explorer Score: 0.28.

Base model:quantized:thedrumme... Base model:thedrummer/orion-26...   Conversational   Creative-writing   En   Fp8   Gemma4   Modelopt   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bandageshi/Orion-26B-A4B-v1.1-FP8-Dynamic 

Orion 26B A4B V1.1 FP8 Dynamic Parameters and Internals

LLM NameOrion 26B A4B V1.1 FP8 Dynamic
Repository 🤗https://huggingface.co/bandageshi/Orion-26B-A4B-v1.1-FP8-Dynamic 
Base Model(s)  TheDrummer/Orion-26B-A4B-v1.1   TheDrummer/Orion-26B-A4B-v1.1
Model Size26b
Required VRAM27.1 GB
Updated2026-09-24
Maintainerbandageshi
Model Typegemma4
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   7.1 GB: 3-of-3
Supported Languagesen
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.14.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Orion 26B A4B V1.1 FP8 Dynamic

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 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
Note: green Score (e.g. "73.2") means that the model is better than bandageshi/Orion-26B-A4B-v1.1-FP8-Dynamic.