Ask HN: Isn't there a simpler way to run LLMs / models locally?
I'm currently exploring a project idea : *create an ultra-simple tool for launching open source LLM models locally, without the hassle, and I'd like to get your feedback.*
### The current problem:
I'm not a dev or into IT or anything, but I've become fascinated by the subject of local LLMs , but running an LLM model on your own PC can be a real pain in the ass :
Installation and hardware compatibility.
Manual management of models and dependencies.
Interfaces often not very accessible to non-developers.
No all-in-one software (internet search, image generation, TTS, etc.).
Difficulty in choosing the right model for one's needs, so you get the idea.
I use LM studio, which I think is the simplest, but I think you can do a lot better than that.
### The idea :
A software / app that lets you install and use in 1 click, for everyone.
Download and fine-tune a model easily.
Automatically optimize parameters according to hardware.
Create a pretty, intuitive interface.
Anyway, I have lots of other ideas but that's not the point.
### Why am I posting here?
I'm looking to *validate this idea* before embarking on MVP development, and I'd love to hear from all you HN contributors ! :)
- What are the biggest problems you've encountered when launching a local LLM ? - How are you currently doing and what would you change/improve ? - Do you see any particular use cases (personal, professional, business) ? - What a question I didn't ask you that deserves an answer anyway ;)
I sincerely believe that current solutions can be vastly improved.
If you're curious and want to follow the evolution of the project, I'd be delighted to exchange in PM or in the comments, maybe in the future I'll be looking for early adopters!
Thanks in advance for your feedback