Whistle: Speech to Text in 16.9 MB
Cactus Compute’s Whistle packs on-device speech recognition into one 16.9 MB file: no GPU, no dependencies, seven languages, word timestamps...
Oct 9, 2026
5 min
EmbeddingGemma 2: One Small Open Model for Searching Text, Code, Images, Video and Audio
EmbeddingGemma 2 is a 740M-parameter open model from Google that searches five kinds of content with a single set of vectors. Here's what's ...
Oct 7, 2026
8 min
The Tiny AI Pocket: Inside Tiiny AI's 120-Billion-Parameter Pocket Supercomputer
A technical breakdown of the Tiiny AI Pocket Lab, the pocket-sized device running 120-billion-parameter language models offline, the TurboSp...
Sep 8, 2026
9 min
Apple's Mac Studio Is Becoming an AI Workstation as Enterprise AI Demand Grows
Apple's latest Mac Studio pushes beyond the traditional workstation with enormous unified memory, dedicated AI acceleration, and distributed...
Sep 1, 2026
6 min
Margin Collapse Fuels the Rise of On‑Device, Open‑Source AI Ecosystems | The AI Daily Roundup
As inference margins shrink, developers and firms are turning to cheaper on‑device hardware, open‑source models like GLM 5.2, and agent‑cent...
Jul 7, 2026
3 min