GoogleReleased on Jun 10, 2026

DiffusionGemma 26B-A4B: Benchmarks, Pricing & Context Window

DiffusionGemma 26B-A4B is a language model from Google, released in June 2026, with multimodal input.

DiffusionGemma 26B-A4B is Google DeepMind's experimental open-weights text diffusion model based on the Gemma 4 26B-A4B Mixture-of-Experts architecture. It uses discrete diffusion to denoise 256-token canvases in parallel, targeting

DiffusionGemma 26B-A4B API

API access coming soon

DiffusionGemma 26B-A4B will be available through our gateway shortly.

DiffusionGemma 26B-A4B examples

Recent arena outputs from DiffusionGemma 26B-A4B, picked from the highest-ranked matchups.

DiffusionGemma 26B-A4B license

DiffusionGemma 26B-A4B is released under the Apache 2.0 license, which permits commercial use, has 25.2B parameters, has a knowledge cutoff of January 2025.

License
Apache 2.0
Commercial use allowed
Parameters
25.2B
Knowledge cutoff
January 2025

Apache License 2.0 - allows commercial use

FAQ

Common questions about DiffusionGemma 26B-A4B.

What is the DiffusionGemma 26B-A4B release date?

DiffusionGemma 26B-A4B was released on June 10, 2026 by Google.

Who created DiffusionGemma 26B-A4B?

DiffusionGemma 26B-A4B was created by Google.

How many parameters does DiffusionGemma 26B-A4B have?

DiffusionGemma 26B-A4B has 25.2 billion parameters.

What is the license for DiffusionGemma 26B-A4B?

DiffusionGemma 26B-A4B is released under the Apache 2.0 license. This is an open-source/open-weight license.

What is the knowledge cutoff date for DiffusionGemma 26B-A4B?

DiffusionGemma 26B-A4B has a knowledge cutoff of January 2025. This means the model was trained on data up to this date and may not have information about events after this time.

Is DiffusionGemma 26B-A4B multimodal?

Yes, DiffusionGemma 26B-A4B is a multimodal model that can process both text and images as input.