this post was submitted on 28 Oct 2025
41 points (87.3% liked)

Linux

13757 readers
104 users here now

Welcome to c/linux!

Welcome to our thriving Linux community! Whether you're a seasoned Linux enthusiast or just starting your journey, we're excited to have you here. Explore, learn, and collaborate with like-minded individuals who share a passion for open-source software and the endless possibilities it offers. Together, let's dive into the world of Linux and embrace the power of freedom, customization, and innovation. Enjoy your stay and feel free to join the vibrant discussions that await you!

Rules:

  1. Stay on topic: Posts and discussions should be related to Linux, open source software, and related technologies.

  2. Be respectful: Treat fellow community members with respect and courtesy.

  3. Quality over quantity: Share informative and thought-provoking content.

  4. No spam or self-promotion: Avoid excessive self-promotion or spamming.

  5. No NSFW adult content

  6. Follow general lemmy guidelines.

founded 2 years ago
MODERATORS
MigratingtoLemmy@lemmy.world
41
Anyone messed with local cli LLMs? (sh.itjust.works)
submitted 3 days ago by bridgeenjoyer@sh.itjust.works to c/linux@lemmy.world
23 comments fedilink hide all child comments
 

Let me preface by saying I despise corpo llm use and slop creation. I hate it.

However, it does seem like it could be an interesting helpful tool if ran locally in the cli. I've seen quite a few people doing this. Again, it personally makes me feel like a lazy asshole when I use it, but its not much different from web searching commands every minute (other than that the data used in training it is obtained by pure theft).

Have any of you tried this out?

you are viewing a single comment's thread
view the rest of the comments
[–] domi@lemmy.secnd.me 7 points 3 days ago

I'm running gpt-oss-120b and glm-4.5-air locally in llama.cpp.

It's pretty useful for shell commands and has replaced a lot of web searching for me.

The smaller models (4b, 8b, 20b) are not all that useful without providing them data to search through (e.g. via RAG) and even then, they have a bad "understanding" of more complicated prompts.

The 100b+ models are much more interesting since they have a lot more knowledge in them. They are still not useful for very complicated tasks but they can get you started quite quickly with regular shell commands and scripts.

The catch: You need about 128GB of VRAM/RAM to run these. The easiest way to do this locally is to either get a Strix Halo mini PC with 128GB VRAM or put 128GB of RAM in a server/PC.