LLM EXPLORER 61,918 MODELS INDEXED

Diffusiongemma 26B A4B It NVFP4 by nvidia

By nvidia · 1881298 downloads
HF Repo ↗ Copy URL

Diffusiongemma 26B A4B It NVFP4 is an open-source language model by nvidia. Features: 26b LLM, VRAM: 18.8GB, License: apache-2.0, LLM Explorer Score: 0.4.

  8-bit Base model:google/diffusiongem... Base model:quantized:google/di...   Conversational   Diffusion gemma   Diffusiongemma-26b-a4b-it   Modelopt   Nvfp4   Nvidia   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/diffusiongemma-26B-A4B-it-NVFP4 

Diffusiongemma 26B A4B It NVFP4 Parameters and Internals

LLM NameDiffusiongemma 26B A4B It NVFP4
Repository 🤗https://huggingface.co/nvidia/diffusiongemma-26B-A4B-it-NVFP4 
Base Model(s)  Diffusiongemma 26B A4B It   google/diffusiongemma-26B-A4B-it
Model Size26b
Required VRAM18.8 GB
Updated2026-07-20
Maintainernvidia
Model Typediffusion_gemma
Model Files  10.0 GB: 1-of-2   8.8 GB: 2-of-2
Model ArchitectureDiffusionGemmaForBlockDiffusion
Licenseapache-2.0
Transformers Version5.8.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Diffusiongemma 26B A4B It NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
Diffusiongemma 26B A4B It0K / 51.6 GB18994721167
OUI 10K / 51.6 GB45681
...iffusiongemma 26B A4B It NVFP40K / 18.1 GB24110919
Diffusiongemma 26B A4B It0K / 51.6 GB102056
...emma 26B A4B It Int4 AutoRound0K / 29.3 GB53033
...ngemma 26B A4B It ALWAYS THINK0K / 51.6 GB970
...iffusiongemma 26B A4B It Mxfp40K / 14.8 GB6166
...Gemma 26B E38 Abliterated BF160K / 51.6 GB390
...iffusiongemma 26B A4B It Nvfp40K / 15.6 GB2425
Diffusiongemma 26B A4B It0K / 51.6 GB481
Note: green Score (e.g. "73.2") means that the model is better than nvidia/diffusiongemma-26B-A4B-it-NVFP4.