News for hackers. Stuff that matters.

A comment on GPT-5 is behind schedule. Parent comment

Re:GPT-5 is behind schedule by SamPatt on Monday December 23, 2024 @01:39PM (#42496603)
How will they do this?

You can't take the free stuff away. It's on my hard drive.

They can stop releasing them, but local models aren't going anywhere.

[ Parent | on HN ]
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 ]
Re:GPT-5 is behind schedule by skirmish on Thursday December 26, 2024 @12:44AM (#42513374)
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 .
[ Parent | on HN ]
Re:GPT-5 is behind schedule by dns_snek on Tuesday December 24, 2024 @04:37AM (#42500775)
They can't take the current open models away, but those will eventually (and I imagine, rather quickly) become obsolete for many areas of knowledge work that require relatively up to date information.
[ Parent | on HN ]