Qwen3 as well as Kimi K2 keep stopping mid-chat
At some point they stop calling tools, and in the case of Qwen3 it just keeps looping when i tell it to carry on. Using OpenRouter as the model provider
https://github.com/user-attachments/assets/2facd4ae-db1e-4995-a389-d538bde8dea1
I have the same issue using 0.3.110 with Qwen 3 Coder @ openrouter either free or paid. Went back to Claude.
when this happens, i check the activities page on OpenRouter and see this. A 0.3 TPS may be the cause of this.
My TPS doesn't drop quite that low, but I do see "STOP" coming in
Same issue when trying to run qwen3 via ollama, tool calling stops working and few messages in.
for local don't use ollama use LM studio beta
for qwen3 coder i recommend using alibaba directly - a lot of openrouter providers are unreliable
I think openRouter automatically routes it to the next one if the request fails -- Qwen3 Coder works fine via Roo Code / Cline, I wonder if they have some sort of retry logic in there
for local don't use ollama use LM studio beta
Using llama.cpp, it seems to also work very well. (Tried with qwen3-coder-30b.)
I'm also having this issue with Kimi 2 Thinking using OpenCode Zen.