LLM EXPLORER 61,755 MODELS INDEXED

Gemma 4 26B A4B It NVFP4 by bg-digitalservices

By bg-digitalservices · 15038 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B It NVFP4 is an open-source language model by bg-digitalservices. Features: 26b LLM, VRAM: 16.4GB, License: apache-2.0, LLM Explorer Score: 0.29.

  8-bit Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Blackwell   Conversational   Dgx-spark   Endpoints compatible   Gemma4   Image-text-to-text   Modelopt   Moe   Multilingual   Nvfp4   Nvidia   Post-training-quantization   Quantized   Region:us   Safetensors   Sharded   Tensorflow   W4a4
Model Card on HF 🤗: https://huggingface.co/bg-digitalservices/Gemma-4-26B-A4B-it-NVFP4 

Gemma 4 26B A4B It NVFP4 Parameters and Internals

LLM NameGemma 4 26B A4B It NVFP4
Repository 🤗https://huggingface.co/bg-digitalservices/Gemma-4-26B-A4B-it-NVFP4 
Base Model(s)  Gemma 4 26B A4B It   google/gemma-4-26B-A4B-it
Model Size26b
Required VRAM16.4 GB
Updated2026-09-20
Maintainerbg-digitalservices
Model Typegemma4
Model Files  8.0 GB: 1-of-3   8.0 GB: 2-of-3   0.4 GB: 3-of-3
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4B It NVFP4

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 GB2854528
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
WaifuGemma4 26B A4b V10K / 51.6 GB85010
Gemma 4 26B A4B It NVFP40K / 16.9 GB15466321
Gemma 4 26B A4B It FP8 Dynamic0K / 28.6 GB113634938
Note: green Score (e.g. "73.2") means that the model is better than bg-digitalservices/Gemma-4-26B-A4B-it-NVFP4.