PaperLens
紙
Students
Professional
JA
EN
◐
Sign in with Google
Sign in
Read
Home
Close reading
New
Textbook
Go deeper
Learn
Lab
Landscape
Contributors
Glossary
You
Search
All-access
My Page
#edge-inference
1 articles
01
2026-08-27
·
Agents
·
★ MEMBER
·
PAPER
·
13 min read
Paper Explained: FreeToken — Treating Your Own PC as a Single Elastic Inference Platform
FreeToken is an edge-native serving system for frontier-scale MoE models on personal hardware. Its centerpiece is a q* policy that decides how many missed experts to ship over PCIe versus execute in place on the CPU — using nothing but two measured bandwidths.