google/diffusiongemma-26B-A4B-it · Hugging Face
huggingface.co · 2,449 words · saved by 1 readers
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face | GitHub | Launch Blog | Documentation License: Apache 2.0 | Authors: Google DeepMind DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output. Built on a MoE foundation, DiffusionGemma is designed to improve generation speed (tokens per second) while remaining deployable across various hardware environments. DiffusionGemma builds upon the…
saved by
related reading
- A Visual Guide to DiffusionGemma - by Maarten Grootendorstnewsletter.maartengrootendorst.com
- GitHub - google/hackable_diffusiongithub.com
- dealignai/Gemma-4-12B-it-qat-JANG_4M-CRACK · Hugging Facehuggingface.co
- Diffusion will be everywherevarunneal.github.io
- Gemma 4deepmind.google
- Llama 2 · Hugging Facehuggingface.co
- What are Diffusion Models?lilianweng.github.io
- VaultGemma: The world's most capable differentially private LLMresearch.google
- Neuronpedianeuronpedia.org
- Gemma 2: Improving Open Language Models at a Practical Sizearxiv.org
- Hugging Face – The AI community building the future.huggingface.co
- Large Language Diffusion Modelsarxiv.org