I’ve tried coding and every one I’ve tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.
I’ve tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.
So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can’t really handle anything above 4B in a timely manner. 8B is about 1 t/s!
I’ve run a few models that I could on my GPU. I don’t think the smaller models are really good enough. They can do stuff, sure, but to get anything out of it, I think you need the larger models.
They can be used for basic things, though. There are coder specific models you can look at. Deepseek and qwen coder are some popular ones
I haven’t actually found the coder-specific ones to be much (if at all) better than the generic ones. I wish I could have. Hopefully LLMs can become more efficient in the very near future.
Been coming to similar conclusions with some local adventures. It’s decent but not as able to process larger contexts.