Google's Gemma 4 open AI models use "speculative decoding" to get up to 3x faster Up to 3x the speed with no loss of quality—is it too good to be true? https://arstechnica.com/ai/2026/05/googles-gemma-4-open-ai-models-use-speculative-decoding-to-get-up-to-3x-faster/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social