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.

Ask HN: If you're running an LLM locally, what are you using?

5 pointsby nomilkover 1 year ago
As in title, if you&#x27;re self-hosting an LLM, which one are you using and how did you set it up.<p>For context, I got an image generator running locally in about 20 minutes (Fooocus). Keen to try the same with LLM.

3 comments

smoldesuover 1 year ago
I recently found out about llama-cpp&#x27;s official &quot;Server&quot; function: <a href="https:&#x2F;&#x2F;github.com&#x2F;ggerganov&#x2F;llama.cpp&#x2F;blob&#x2F;master&#x2F;examples&#x2F;server&#x2F;README.md">https:&#x2F;&#x2F;github.com&#x2F;ggerganov&#x2F;llama.cpp&#x2F;blob&#x2F;master&#x2F;examples&#x2F;...</a><p>Works like a charm for my (simple) use case. I&#x27;m running it on an Always Free Oracle Ampere A1 instance with 4 cores and ~20gb of memory. (Obligatory &quot;fuck Larry Ellison&quot; here)
kungfupawndaover 1 year ago
I am running ollama on my MSI GP76 windows laptop with RTX 3080 card and 64 gb ram. It&#x27;s running on the baked in linux installation. It recognized the graphics card right away and works pretty well. On my macbook pro m3 max with 36 GB ram, I can&#x27;t run the 70B parameter model.
kaashmoneeover 1 year ago
Ollama is incredible for me! The setup was super easy. I have been playing around with llama2-uncensored.
评论 #39292295 未加载