site banner

Friday Fun Thread for January 31, 2025

Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.

2
Jump in the discussion.

No email address required.

...

I'm horrified that there are guides that lead people to use a 4090 to barely run a 14B model at .6t/s.

For clarity, with a single 4090 you should be able to run 14B at 8bit (near-flawless quality) and probably get more than 40T/s with tons of space left over for context. But you'd be better off running a 32B at 4-5bit, which should still have low quantization loss and massively better quality due to the model being larger. You can even painfully squeeze a 70B in there, but the quality loss is probably not worth it at the required ~2bit. All of those should run at 20-30 T/s minimum.

I think vllm is meant for real production use on huge servers. For home use I'd start with koboldcpp (really easy), llamacpp (requires cli) or ooba/tabbyapi with exl2. The latter is faster on pure gpu but has the downside that you have to deal with python instead of being pure standalone.

...