Installed models
| Name | Family | Params | Quant. | Size | Location | Available | |
|---|
Models are never downloaded automatically. To install one, check free disk and RAM first, then run on the server: ollama pull <model>. Smaller models (for example qwen3:4b or llama3.2:3b) respond faster on CPU-only servers.
API keys
| Name | Key | Owner | Scopes | Status | Expires | Last used | |
|---|
Usage (last 7 days)
By model
| Model | Requests | Output tokens | Avg latency |
|---|
By API key
| Key | Requests | Failed | Output tokens |
|---|
Recent operational errors
| Time | Route | Status | Category | Request ID |
|---|