Open Source14d ago
Detected, not submitted
slotstream
Own slotstream?
Verify your site to claim this listing and get emailed the moment a buyer's looking for something like it.
A way to run large language models like Qwen 3.8B on low-memory Macs by using expert-offloading and SSD-streaming to reduce memory requirements from 100GB+ to as little as 16GB.
Spotted on Hacker News on September 1, 2026.
CA
carloslfu
Maker