GitHub - sqliteai/waste: Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

Show HN: Run Full Kimi K3 with 29 GB of RAM

Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine. - sqliteai/waste

8 points by marcobambini 84 days ago github.com 2 comments

Summary not yet generated for this article.

Comments (2 of ) ⌛

Loading more comments... ⌛

Scroll down to load more comments

No comments available.