Almost every large language model (LLM) in wide use today is autoregressive — meaning it generates text one token at a time, with each new word depending on the one before it. That sequential process is what makes interactive AI feel like it’s typing.

DiffusionGemma takes a different path. Built on the Gemma 4 26B mixture-of-experts architecture, it generates text the way diffusion models generate images: by starting from noise and refining a whole block of text at once. Each step denoises up to 256 tokens in parallel rather than emitting a single token and waiting to compute the next.

The result is a model that thinks in blocks instead of sequentially. For latency-sensitive, single-user work — such as interactive chat, agentic loops or on-device assistants that plan and act — that parallelism translates into responses fast enough to keep pace with how developers think and iterate.

Generating one token at a time is fundamentally a memory-bound problem — a traditional LLM spends most of its time waiting on memory bandwidth, not doing math, which leaves a lot of compute on the table.