On-Device & Local InferenceGoogle (Chrome)Google

Chrome 148 stable opens the Prompt API to the web

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Opened the Prompt API to the web in Chrome 148 stable — for extensions it has been stable since Chrome 138. Web pages access the browser's built-in Gemini Nano directly, with support for text, image and audio input and for constraining responses with regular expressions and JSON schemas. Requirements: 22GB of free space, and more than 4GB of VRAM or 16GB of RAM and 4 or more cores

Why it matters

A stable-channel case of an on-device model exposed as a web platform API rather than an app. Responsibility for model distribution and storage management passes to the browser vendor

Source — Primary sources first; secondary reports are labelled “Press”

Officialdeveloper.chrome.comhttps://developer.chrome.com/release-notes/148

Added in Week 36, 2026 · See that week

On the map — ⑲ On-Device line

  1. Previous stopGoogle releases Gemma 4 as an AICore developer preview
  2. This recordPrompt API to the web
  3. Next stopLiteRT-LM
See it on the map

Related notes — Notes on the same axis from the same week

A local AI design that handles prefill and decode on different chipsPackaging is the secret behind a 6 nm chip's bandwidth win

Same week

Iwase et al. publish Reliable Chain-of-Thought via Prefix ConsistencyPaperTeaching Claude WhyOfficialStop Comparing LLM Agents Without Disclosing the HarnessPaperGPT-Realtime-2 / -Translate / -WhisperOfficial

Nearby on the same axis

Google makes LiteRT-LM generally available (GA)Officialllama.cpp Discussion #23853 shares an NVFP4/MXFP6 mixed-precision toolOfficialMicrosoft makes Foundry Local generally available (GA)OfficialOllama 0.30 adds llama.cpp-based GGUF compatibility to its MLX engineOfficial