GoogleReleased on Jun 10, 2026

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

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 benchmarks

Rankings

Quality Tracker

DiffusionGemma 26B-A4B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Sat Jul 18 2026
Notice missing or incorrect data?

DiffusionGemma 26B-A4B model size

DiffusionGemma 26B-A4B has 25.2 billion parameters. See how it compares to other models in the same parameter range.

Parameters
25.2BMoE
Medium (10–30B)
25.2B
1B7B70B405B

DiffusionGemma 26B-A4B latency

DiffusionGemma 26B-A4B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

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

DiffusionGemma 26B-A4B resources

Official sources for DiffusionGemma 26B-A4B: official launch post, model weights.

DiffusionGemma 26B-A4B vs other models

The most-compared alternatives to DiffusionGemma 26B-A4B are DeepSeek R1 Zero, LongCat-Flash-Chat, Claude 3.5 Sonnet. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like DiffusionGemma 26B-A4B

Models ranked just above and below DiffusionGemma 26B-A4B by LLM Stats score.

 

DeepSeek R1 Zero

Score pending
DetailsCompare
 

LongCat-Flash-Chat

Score pending
DetailsCompare
 

Claude 3.5 Sonnet

Score pending
DetailsCompare
 

Qwen3 VL 32B Thinking

Score pending
DetailsCompare
 

Sarvam-105B

Score pending
DetailsCompare
 

Qwen3 VL 8B Thinking

Score pending
DetailsCompare

FAQ

Common questions about DiffusionGemma 26B-A4B.

When was DiffusionGemma 26B-A4B released?

DiffusionGemma 26B-A4B was released on June 10, 2026 by Google. This is the official DiffusionGemma 26B-A4B release date tracked on LLM Stats.

How big is DiffusionGemma 26B-A4B?

DiffusionGemma 26B-A4B has 25.2 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created DiffusionGemma 26B-A4B?

DiffusionGemma 26B-A4B was created by Google.

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 that permits self-hosting.

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

DiffusionGemma 26B-A4B has a knowledge cutoff of January 2025, meaning it was trained on data up to that point and may not know about events after it.

Is DiffusionGemma 26B-A4B multimodal?

Yes, DiffusionGemma 26B-A4B is multimodal and can accept both text and images as input.

Where is the DiffusionGemma 26B-A4B paper or technical report?

DiffusionGemma 26B-A4B has a paper or technical report available at https://blog.google/innovation-and-ai/technology/developers-tools/diffusion-gemma-faster-text-generation/. Use that source for architecture, training, release and evaluation details.

What models should I compare DiffusionGemma 26B-A4B against?

Common DiffusionGemma 26B-A4B comparisons include DiffusionGemma 26B-A4B vs DeepSeek R1 Zero, DiffusionGemma 26B-A4B vs LongCat-Flash-Chat, DiffusionGemma 26B-A4B vs Claude 3.5 Sonnet. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.