23 updates on Google.
FunctionGemma 270M fine-tune reaches 76.5% on 15 mobile actions, with an Android demo
Fine-tuning FunctionGemma 270M on 9,500 synthetic mobile-action conversations raises end-to-end accuracy from 29.3% to 76.5%, with a Pixel 8 Pro demo app.
Google adds local model support to the Antigravity SDK with Gemma 4 on LiteRT
Antigravity agents can now run on Gemma 4 26B A4B through LiteRT, with Google recommending more than 24 GB of VRAM or unified memory.
MediaTek launches Dimensity CX C10 Max, a 55 TOPS chip for Googlebook
MediaTek’s Dimensity CX C10 Max is a 3nm chip with a 55 TOPS NPU built for Google’s new Googlebook laptop category.
Qualcomm's Snapdragon X Elite powers the first Googlebook laptops from Dell and HP
The Dell XPS Googlebook 13 and HP Googlebook 14 use the Snapdragon X Elite and its 45 TOPS NPU to run Gemini Intelligence features, with pre-orders open.
Google releases ADK for Kotlin 1.0 with on-device agents for Android
ADK for Kotlin 1.0 adds Android modules that run agents on the device with Gemma through LiteRT-LM and Gemini Nano through ML Kit.
Google lists first Gemini Nano 4 phones, requires Nano 3 for Gemini Intelligence
ML Kit GenAI documentation now names nano-v4 devices and sets Nano v3 or greater, plus 12 GB of RAM, as the requirement for Gemini Intelligence.
Pixel Watch 5 adds offline Gemini commands and faster on-device smart replies
Offline voice commands on the Pixel Watch 5 run on an on-device model, and a Gemini Nano upgrade makes smart replies 50 percent faster.
Pixel 11 series: Tensor G6 adds 50 percent more TPU compute
Google says Tensor G6 with the latest Gemini Nano model processes on-device AI tasks up to 3.5 times faster while using up to 3.5 times less energy.
Gemini Nano 4 ships on Samsung foldables with ML Kit Prompt API access
Google says Samsung’s new foldables carry Gemini Nano 4 with support for more than 140 languages, reachable from apps through ML Kit’s Prompt API.
MobiBench paper benchmarks small LLMs in llama.cpp on two laptops and an RTX 3060
MobiBench is a llama.cpp benchmark suite for speed, memory and accuracy of small LLMs, but the reported tests ran on two laptops and not on phones.
Google adds multi-token prediction to Gemini Nano v3 on Pixel 9 and 10
Google added a prediction head to frozen Gemini Nano v3 on Pixel 9 and 10, saving 130 MB per instance over a standalone drafter.
LiteRT-LM reports 52 decode tokens per second for Gemma 4 E2B on an Android GPU
Google publishes prefill and decode figures for its on-device runtime, adds Swift and JavaScript APIs, and reports a 2.2x speedup from multi-token prediction.