AirLLM: Inference 2.8T Kimi K3 on a single 4GB GPU (github.com)

2 points by maxloh 2mo ago ↗ HN

0 comments

[ 2.7 ms ] story [ 10.5 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats