OpenCode Go Performance is abysmal #17173

Activity

1. cw-1988

   added

   bugSomething isn't workingSomething isn't working

   on Mar 12, 2026
2. github-actions

   assigned

   rekram1-node

   on Mar 12, 2026
3. github-actions

   added

   coreAnything pertaining to core functionality of the application (opencode server stuff)Anything pertaining to core functionality of the application (opencode server stuff)

   nix

   perfIndicates a performance issue or need for optimizationIndicates a performance issue or need for optimization

   on Mar 12, 2026
4. github-actions commented on Mar 12, 2026

   

   github-actionsBot

   on Mar 12, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of existing issues. Please check:

   • Anyone experiencing GLM performance with the new quota? #14011: GLM performance issues reported by other users
   • GLM 4.7 Max sub is slow and dumb #10738: GLM 4.7 being slow
   • Poor performance with local models #4385: Poor performance with local models

   If your issue is distinct (e.g., specific to a particular version or tool-call behavior), please add more detail to differentiate it.
5. cw-1988 commented on Mar 12, 2026

   

   cw-1988

   on Mar 12, 2026

   Author

   More actions

   It's mainly about server response/queue times with the Go subscription...
6. thdxr

   removed

   bugSomething isn't workingSomething isn't working

   perfIndicates a performance issue or need for optimizationIndicates a performance issue or need for optimization

   nix

   coreAnything pertaining to core functionality of the application (opencode server stuff)Anything pertaining to core functionality of the application (opencode server stuff)

   on May 3, 2026
7. agung2001 commented on Jun 24, 2026

   

   agung2001

   on Jun 24, 2026

   More actions

   have the same issue. the response is very slow.
8. sudo-tee commented on Jun 29, 2026

   

   sudo-tee

   on Jun 29, 2026

   Last edited by sudo-tee

   More actions

   I just subscribed to Go to test GLM 5.2 and the performance is really bad. Every tool call and messages takes over 30 seconds each.

   At the moment I have a vbetter experience with deepseek-v4-flash free than any models on Go.

   👍React with 👍1Reacted by Alejandro Castrillón
9. fwang commented on Jun 29, 2026

   

   fwang

   on Jun 29, 2026

   Contributor

   More actions

   @sudo-tee had an temporary issue with upstream GLM 5.2 provider.

   give it a try again

   👎React with 👎1Reacted by Alejandro Castrillón
10. fwang

    closed this as completedon Jun 29, 2026