Google DeepMind has released DiffusionGemma, a 26B open model that uses text diffusion instead of autoregressive decoding. The approach generates entire blocks of text in parallel, delivering up to 4x faster generation on GPUs than standard models. It fits in 18GB of VRAM and runs at 1000+ tokens per second on an H100. https://arstechnica.com/google/2026/06/googles-latest-diffusiongemma-open-ai-model-comes-with-a-4x-speed-boost/ #AIagent #AI #GenAI #AIResearch
Related
Integrar IA en .NET normalmente significa pelear con diferentes SDKs para OpenAI, Ollama, Google... ¡Es un lÃo, ¿verdad?...
Integrar IA en .NET normalmente significa pelear con diferentes SDKs para OpenAI, Ollama, Google... ¡Es un lÃo, ¿verdad?!â–¶ Full write-up: https://jocheojeda.com/2026/06/10/getting-...
https://www.youtube.com/shorts/J3QIBMW4InM#AI
https://www.youtube.com/shorts/J3QIBMW4InM#AI
Apple’s new software drops support for these 16 productsiOS 27 is compatible with all the same iPhones as last year’s iO...
Apple’s new software drops support for these 16 productsiOS 27 is compatible with all the same iPhones as last year’s iOS 26, but almost every other software platform drops multipl...