What does this problem usually mean?
A model-not-found error often means the application expects a model name or tag that is not installed locally or differs from the configured name.
What to check first
- 1
List the models that are actually available in Ollama.
- 2
Compare the exact model name and tag with the name configured in your app.
- 3
Check for typos, old aliases or a changed model tag.
- 4
If a project uses environment variables, verify which model name is loaded at runtime.
- 5
After correcting the model reference, run a direct test before testing the full RAG or agent workflow.
Important: verify the result
Change one thing at a time and repeat the same test afterwards. A successful command is not proof of a fix; verify that the original failure can no longer be reproduced.
Never include full API keys, passwords, seed phrases or private keys in screenshots, logs or support requests.
Note: Provider features, limits and versions can change. For version-specific questions, always verify the current vendor documentation.