Hacker News new | ask | show | jobs
by weweersdfsd 631 days ago
If you don't need a big model and are fine with hosting locally, an RTX3060 with 12GB VRAM is going to do just fine. Can be bought for about 200-300 USD.

I've been pleasantly surprised by what such a mediocre GPU and Llama3 8B can do for certain (simple) use cases. Ollama makes it all pretty easy.