Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU

github.com

Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU

github.com

RSS BotBM to Hacker NewsEnglish · 1 day ago

GitHub - AmSach/maple: MAPLE: Manifold-Activated Pruning of Latent Experts for Sub-2-BPW MoE LLMs

github.com

MAPLE: Manifold-Activated Pruning of Latent Experts for Sub-2-BPW MoE LLMs - AmSach/maple

Comments

You must log in or register to comment.

Chat

Hacker News

hackernews

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.bestiver.se

Community locked: only moderators can create posts. You can still comment on posts.

NOTICE: The bot occasionally has downtime, sorry about that. I’m working on adding better monitoring and error recovery so I can get notified faster.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Source of the RSS Bot.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

744 users / day
2.23K users / week
4.06K users / month
8.84K users / 6 months
2 local subscribers
5.73K subscribers
64.7K Posts
35.5K Comments
Modlog