News for hackers. Stuff that matters.

A comment on Building a Deep Learning Rig. Parent comment

Re:Building a Deep Learning Rig by fragmede on Saturday February 24, 2024 @05:29PM (#39495709)
It depends on what you're trying to do, but I've got an M1, and doing inference with llama2-uncensored using Ollama, I get results within seconds.
[ Parent | on HN ]
Re:Building a Deep Learning Rig by whywhywhywhy on Saturday February 24, 2024 @07:47PM (#39496567)
Depends what you're doing, M1 Max is around a minute for 1 SDXL image and the machine feels like it's choking while it does it while a 3090 will do it in 9 seconds and doesn't feel like it's breaking a sweat.

Llama definite a bit of a different story though.

[ Parent | on HN ]
Re:Building a Deep Learning Rig by jeffybefffy519 on Sunday February 25, 2024 @06:06PM (#39505883)
Im more thinking about the training side because it could be compelling to buy a beefily specced m3 max if it can replace what a dedicated gpu rig could do and also be a daily driver.
[ Parent | on HN ]