unknown model koboldcpp
✅Solved
when i check my models list with openclaw models list i can see only 1 model there, the one model i have
and in the config i have the same model set but it still tells me the Agent failed before reply: Unknown model: koboldcpp/Qwen3-8B-Q8_0
im trying to run a local llama llm
i have the api key and base url set as well
i made sure the local url has the /v1 for the api key access
i did a reset as well using "openclaw gateway --tailscale serve --force" to reboot
and in the config i have the same model set but it still tells me the Agent failed before reply: Unknown model: koboldcpp/Qwen3-8B-Q8_0
im trying to run a local llama llm
i have the api key and base url set as well
i made sure the local url has the /v1 for the api key access
i did a reset as well using "openclaw gateway --tailscale serve --force" to reboot
Solution
Providers w/ OAuth/tokens (0)baseUrl + apiKeyThe two useful bits from what you pasted:
- Your Control UI is at
http://127.0.0.1:18789/gateway.controlUi.basePath- The
404 (no body)Step 1: Is the dashboard itself 404’ing, or only when you try to chat?
Run this and paste the first line (status) + maybe 2-3 headers:- If that returns HTTP 200 → dashboard assets are fine, and your 404 is coming from the model provider requests when you try to chat.
- If that returns HTTP 404 → the gateway isn’t serving the Control UI (common if running from source without building UI).
The AI that actually does things. Emails, calendar, home automation - all from your favorite chat app. New shell, ready to help. The lobster way.
131,281Members
Resources
Recent Announcements
Similar Threads
Was this page helpful?
