This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Rafal
potato.horse
did:plc:xwlabnj73xb6hajquk4vtlp3
What are the best LLMs that can be run locally with 48GB of RAM (M4 Pro)?
I don't care whether they're unimodal, multimodal, fine-tuned, censored or uncensored.
I'm equally curious about *what* models you use and *how* you use them. (working on an article for late January)
(CC @simonw) #llm
2024-12-30T13:32:40.321Z