"ResourceExhausted: Worker local total request limit reached (X/32)"
Sup guys, i started using Opencode with the Nvidia NIM api a few days ago.
I tried using some models but on some models i got an error that their life has ended. Other than that ive enjoyed many other models like kimi, minimax, deepseek (untill it started taking decades to respond) and mainly nemotron... The 550B nemotron is a beast. But every now and then im getting this error "ResourceExhausted: Worker local total request limit reached (X/32)" is it fixable or its just the free endpoint experience?
Im working on one AI project and finding and downloading all the models was getting hella repetitive and time exhausting so thats the main reason why i started using agents to work for me... Soo any recommendations for other models are of course welcome :D
Btw running the agent locally isnt really an option since im doing most of my work on my laptop
Thanks for any recommendations