Google's DiffusionGemma writes a paragraph at once — 4x faster, and a bit dumber (blog.google)
It's a 26B Mixture-of-Experts model activating 3.8B params, fitting in 18GB VRAM when quantized — and Google admits output quality trails standard Gemma 4.
A developer who'd used a diffusion model in production said the point isn't 'smart', it's 'stupid fast' — turning prompting back into pair-programming instead of a slot machine.
Sign in to save