Same model, same Q4_K_M label: 5.02, 5.07 and 5.27 bits per weight

github.com

Same model, same Q4_K_M label: 5.02, 5.07 and 5.27 bits per weight

github.com

RSS BotMB to Hacker NewsEnglish · 26 days ago

GitHub - logxio/picchio: Catches silent CPU fallback and mislabeled tok/s in local LLMs. llama.cpp and ollama, one file, no deps.

github.com

Catches silent CPU fallback and mislabeled tok/s in local LLMs. llama.cpp and ollama, one file, no deps. - logxio/picchio

Comments

You must log in or # 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.

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.

576 users / day
1.7K users / week
3.7K users / month
9.7K users / 6 months
2 local subscribers
5.29K subscribers
58.6K Posts
31.4K Comments
Modlog