TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Cohere's minimal compute new LLM

10 pointsby Knajjars2 months ago

1 comment

wizee2 months ago
I tried it out locally and it&#x27;s pretty good. It has a good writing tone and style, and a good level of knowledge, in line with expectations for its size. It&#x27;s slightly worse than Mistral Large 2411 at STEM tasks, but very close in its general level of knowledge, and IMO better than Mistral Large in writing style and creative writing.<p>I also really like the option to choose between the &quot;Strict&quot; and &quot;Contextual&quot; safety modes through the chat template&#x2F;system prompt. It allows censoring the model in a customizable manner for business use cases, while being minimally censored where such restrictions aren&#x27;t needed. It&#x27;s so refreshing to see a good quality model that does what I ask it to do out-of-the-box without condescendingly moralizing, censoring itself, and excessively putting disclaimers everywhere. It&#x27;s so much better than the approach that like likes of Google and Microsoft take with their Gemma and Phi models.<p>In terms of knowledge and intelligence, regardless of Google&#x27;s marketing spin and benchmark gaming, this is vastly superior to yesterday&#x27;s Gemma 3 27b, as you would expect for a model that&#x27;s 4x bigger. I like its default writing style and tone much better than Gemma 3 too. As of today, this and Mistral Large 2411 are the two best models you can run locally within 128 GB of RAM.