Gemma 4 gets a stealth update that fixes tool calling bugs and truncated responses under the same name

Google released a stealth update to its open AI model Gemma 4, fixing tool calling bugs and truncated responses while boosting performance on Nvidia Hopper GPUs by 25-70% with Flash Attention 4. The update also improves image processing with higher resolution support, but the community criticized Google for not versioning it separately.

Gemma 4 gets a stealth update that fixes tool calling bugs and truncated responses under the same name Google shipped an update to its open AI model Gemma 4 that speeds up performance on Nvidia Hopper GPUs, fixes tool calling bugs, and addresses problems with truncated responses. Turning on Flash Attention 4 boosts the speed at which the model processes incoming prompts by 25 to 70 percent, according to Google. Time to first token drops by up to 31 percent. Google also fixed bugs in tool calling, the feature that lets the model trigger external tools on its own. Google says it also cut down on cases where the model would cut answers short or return incomplete responses. For image processing, users can manually raise the "max soft tokens" parameter from 280 to 1,120 to get sharper OCR results and support resolutions up to 2.51 megapixels. Google put up an interactive configurator on Hugging Face https://huggingface.co/spaces/google/gemma4 vision token budget for that. The published benchmarks only compare the 31B and E4B variants against their predecessors, but the Hugging Face repository https://huggingface.co/collections/google/gemma-4 shows that all parameter sizes in this model generation got updated, including the newest 12B release https://the-decoder.com/google-deepminds-gemma-4-12b-squeezes-multimodal-ai-onto-a-laptop-with-just-16-gb-of-ram/ . The community has pushed back on Google shipping the update under the same "Gemma 4" name https://the-decoder.com/googles-gemma-4-is-now-available-with-apache-2-0-licensing-for-the-first-time/ instead of tagging it as a separate version like "Gemma 4.1." AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now X/Google https://x.com/googlegemma/status/2077449152062247219