한국어EN
On-Device & Local InferenceMicrosoft

Microsoft makes Foundry Local generally available (GA)

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

Foundry Local generally available (GA) — a cross-platform on-device inference stack for Windows, Linux and macOS, with automatic GPU, NPU and CPU acceleration and native Metal on Apple Silicon

Why it matters

Made local inference, free of cloud lock-in and per-token billing, an official product line

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

Officialdevblogs.microsoft.comhttps://devblogs.microsoft.com/foundry/foundry-local-ga/

Added in Week 35, 2026 · See that week

On the map — ⑲ On-Device line

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

Same week

Sam Altman blogs on AI power concentration and the OpenAI board conflictOfficialLG AI Research releases EXAONE 4.5 33BOfficialMeta Superintelligence Labs releases Muse SparkOfficialAnthropic signs multi-GW next-gen TPU deal, discloses run-rate revenue over $30BOfficial

Nearby on the same axis

Google releases Gemma 4 as an AICore developer previewOfficialChrome 148 stable opens the Prompt API to the webOfficialllama.cpp merges PR #19769, adding NVFP4OfficialGoogle makes LiteRT-LM generally available (GA)Official