Machine Learning5 min read
Gradium Open-Sources Phonon, a 31M-Parameter On-Device TTS Model Under Apache 2.0
MarkTechPost
Updates on On Device AI
Every AI story we track on On Device AI: 15 stories so far, each summarized in our own words and linked to the publisher that reported it.
Pulled from 125 sources
This week
Machine Learning3 min read
EmbeddingGemma 2 Expands beyond Text to Support Code, Images, Video, and Audio
InfoQ (AI, ML & Data)
This month
Consumer Tech4 min read
Qubo looks to on-device AI to widen smart home adoption in India: CEO Nikhil Rajpal
ET AI (The Economic Times)
Machine Learning3 min read
Google launches EmbeddingGemma 2, an open multimodal embedding model for devices
Covered by 5 sources
OpenBMB Releases MiniCPM5-2B: A 2.52B Dense Model Averaging 53.9 Across 34 Benchmarks and Built to Run On Device
MarkTechPost
Agents11 min read
An iOS app that runs AI agents and a complete voice pipeline on the device
Hacker News
Computer Vision5 min read
LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge
Covered by 2 sources
Agents4 min read
Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights
MarkTechPost
Apple’s real AI story isn’t Siri: it’s a 20-billion-parameter model that runs from your iPhone’s flash
The Next Web
That's everything we have on On Device AI right now