I swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090 (austinsnerdythings.com)

3 points by auspiv 5mo ago ↗ HN

0 comments

[ 3.7 ms ] story [ 14.7 ms ] thread

No comments yet.

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

Source · Live DB stats