The most prestigious law school admissions discussion board in the world.
|
 |
 
|
You can power limit a RTX 3090 to 250W and it still hauls ass at AI
| https://i.imgur.com/chK2k5a.jpeg | 12/12/25 |
| Theory of the Angry Sleep | 12/12/25 |
| average/ordinary/typical citizen/person | 12/12/25 |
| https://i.imgur.com/chK2k5a.jpeg | 12/12/25 |
| average/ordinary/typical citizen/person | 12/12/25 |
| https://i.imgur.com/chK2k5a.jpeg | 12/12/25 |
| average/ordinary/typical citizen/person | 12/12/25 |
| https://i.imgur.com/chK2k5a.jpeg | 12/12/25 |
Poast new message in this thread
Date: December 12th, 2025 8:25 PM Author: https://i.imgur.com/chK2k5a.jpeg It idles around 9W for me, though some people can't get it to idle below 30W which sucks but whatever (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49505831) |
Date: December 12th, 2025 8:26 PM Author: Theory of the Angry Sleep ($noc) (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49505832) |
|
Date: December 12th, 2025 8:27 PM Author: average/ordinary/typical citizen/person What exactly are you even supposed to do with these fraud gpus to make AI happen (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49505835) |
 |
Date: December 12th, 2025 8:39 PM Author: https://i.imgur.com/chK2k5a.jpeg With one you can do inference. With two you can do video and image generation. With four IDK, they say you can do training but I don't care about that (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49505870) |
|
Date: December 12th, 2025 8:51 PM Author: average/ordinary/typical citizen/person What do you mean "do inference" or "do video" what program are you using to do these things? (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49505893) |
|
Date: December 12th, 2025 8:58 PM Author: https://i.imgur.com/chK2k5a.jpeg Ollama is the only platform that's optimized for LLM. You host an Ollama server in a LXC or Docker container, then run Openwebui or AnythingLLM on give it the key to your Ollama server. If you want to run Stable Diffusion you can do it in docker the same way, then access it with ComfyUI in another container. (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49505912) |
|
Date: December 12th, 2025 8:59 PM Author: average/ordinary/typical citizen/person Aight bet i'm not doing any of that shit (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49505917) |
|
Date: December 12th, 2025 10:15 PM Author: https://i.imgur.com/chK2k5a.jpeg Enjoy having all your chats stored in the cloud and used to train models of you I guess (http://www.autoadmit.com/thread.php?thread_id=5809689&forum_id=2],#49506076) |