Anyone running an open source LLM that's better than GPT / Gemini Pro?
| shaky base | 08/01/25 | | shivering crackhouse patrolman | 08/01/25 | | exciting salmon pit keepsake machete | 08/01/25 | | shaky base | 08/01/25 | | shivering crackhouse patrolman | 08/01/25 | | shaky base | 08/01/25 | | cracking selfie area | 08/01/25 | | shivering crackhouse patrolman | 08/01/25 | | cracking selfie area | 08/01/25 | | light chapel | 08/01/25 | | embarrassed to the bone native reading party | 08/01/25 | | Supple smoky church building turdskin | 08/01/25 |
Poast new message in this thread
Date: August 1st, 2025 11:19 AM Author: shivering crackhouse patrolman
you're not going to get better performance from an open source local model unless you've fine tuned it for something specific
the leading frontier models have better pretraining and also waaaay more compute
that being said the new open source models are so good that you can run them locally and get good enough performance. it's just slow
(http://www.autoadmit.com/thread.php?thread_id=5757014&forum_id=2),#49148324) |
 |
Date: August 1st, 2025 11:33 AM Author: shaky base
Which model do you recommended for shitlaw?
And which is best at making videos and creative content?
TYTYTY
(http://www.autoadmit.com/thread.php?thread_id=5757014&forum_id=2),#49148368) |
|
|