Thanks for your continued support. Please advise on your intent to publish Kimi-K3 open-weight models for testing purposes. Your prompt reply and support in taking advantage of this inference model provider’s intelligence as soon as possible, with full context window availability to overcome the 202K context limitation of previous models, are appreciated.
Best Regards.
i doubt they will have the power to give a 3T model for us for free
i mean, if they decreased the rate limit properly i guess they could do it, since nvidia is one of the richest companies in the world
i doubt about that but i still want the kimi k3 to be hosted on the nvidia nim if they want they can remove the model like minimax3, minimax2.7 and kimi k2.6 to make space to host the kimi k3
Hi there,
The build team is constantly trying to bring the latest updates.
Stay tuned!
Best,
Aharpster