Nemotron unusable. Resource exhausted on every request

[ajfbb22]

I’ve created an account to test this model, but every single request I do gives me: “Resource Exhausted: Worker local total request limit reached (X/32)”

[edouard.vincenzi]

I keep getting the same issue asw, seems like the worker limit is especially low on nemotron 3 ultra but also it would be nice to have more in depth documentation about how exactly worker limits and allocation are treated as there isn’t much to go off online.

[diegosch.rosa]

Same here, on opencode, mimo, or claude-code with proxy, all getting the same, can’t use