Anyone running an open source LLM that's better than GPT / Gemini Pro?
| Transparent University | 08/01/25 | | Comical set | 08/01/25 | | Shimmering alpha | 08/01/25 | | Transparent University | 08/01/25 | | Comical set | 08/01/25 | | Transparent University | 08/01/25 | | Charcoal Main People | 08/01/25 | | Comical set | 08/01/25 | | Charcoal Main People | 08/01/25 | | Self-absorbed stead depressive | 08/01/25 | | ruddy nofapping turdskin dysfunction | 08/01/25 | | flatulent lodge fanboi | 08/01/25 |
Poast new message in this thread
Date: August 1st, 2025 11:19 AM Author: Comical set
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: Transparent University
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) |
|
|