Google's new open model DiffusionGemma generates text from noise instead of word by word

Google released DiffusionGemma, a 26-billion-parameter open model that generates text through a diffusion process rather than token-by-token, achieving roughly 1,000 tokens per second on a single Nvidia H100 GPU — about four times faster than comparable autoregressive models. The speed gain comes with lower output quality, leading Google to position the model as an experimental tool for developers.

Google released DiffusionGemma, a 26-billion-parameter model that generates text not token by token but through diffusion, similar to how image AI turns noise into a picture. According to Nvidia, it hits about 1,000 tokens per second on a single H100 GPU, roughly four times faster than comparable autoregressive models. The speed comes at a cost, though. Output quality is lower, so Google is positioning it as an experimental tool for developers for now. The article Google's new open model DiffusionGemma generates text from noise instead of word by word https://the-decoder.com/googles-new-open-model-diffusiongemma-generates-text-from-noise-instead-of-word-by-word/ appeared first on The Decoder https://the-decoder.com .