Re:GPT-5 is behind schedule
by johnisgood on Monday December 23, 2024 @10:12PM
(#42499444)
What are the hardware and software requirements for a self-hosted LLM that is akin to Claude?
[ Parent
| on HN ]
Llama v3.3 70B after quantization runs reasonably well on a 24GB GPU (7900XTX or 4090) and 64GB of regular RAM. Software: https://github.com/ggerganov/llama.cpp .