Waterloo's PAW compiles task specs into 23MB LoRA adapters a 600M-parameter model runs ...

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2, 2026, a system that compiles any natural-language task spec into a 23MB ...
Tech Times

Compile Once, Run Offline: New AI Method Matches 32B Models With a 23MB File

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...
XDA Developers on MSN

I almost upgraded my GPU to run larger local LLMs, but this 8B model proved I didn't have to

The upgrade I almost made wouldn't have solved much ...