Case studies
What teams run on the hardware they already own. And what it took.
The setup, the numbers and the people behind each deployment.
Research with Intel
The methods behind the numbers, co-authored with Intel engineers.
- Read the paper
Paper · October 2026
Cascadia: Resident 975B MoE Inference on Eleven AI PCs
Tate Berenbaum, Matias Parij (Community Labs) · Muthaiah Venkatachalam (Intel)
- Read the paper
Paper · September 2026
Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI Infrastructure
Matias Parij, Pawan Paudel, Tate Berenbaum (Community Labs) · Muthaiah Venkatachalam (Intel)
- Read the paper
Paper · August 2026
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
Tate Berenbaum (Community Labs) · Muthaiah Venkatachalam (Intel)
