article
Running Bonsai 27B as an agent on my phone
Running a 27B model (1-bit) on my phone and letting it perform agentic tasks
apple silicon
Conscious Engines
How we used an ensemble of on-device models to build consumer AI that works offline, costs nothing to run, and never leaves the phone
article
Running a 27B model (1-bit) on my phone and letting it perform agentic tasks
article
A 203M-parameter language model, trained for 14.76B tokens and deployed as one fixed specialist.
article
Optimizing DiffusionGemma (26B-A4B-IT-4Bit) on an Apple M5 Pro, what worked, what didn't.