← Back to Demo
System Monitor
CPU Usage
87%
Memory
42GB
/ 64 GB
GPU VRAM
18.4GB
/ 24 GB
Active Requests
12
GPU Temp
72°C
Disk (NVMe)
1.8TB
/ 2 TB
Queue Depth
3
Uptime
14d
Inference Tokens / sec Avg: 34.2
Network I/O rx: 14MB/s tx: 2MB/s
Service Health
PostgreSQL
Redis
Ollama
MinIO
Temporal
LangGraph
ComfyUI
Grafana
Prometheus
DeerFlow
DRAP
Umami
Loaded Models
| Model | Type | VRAM | Status | Latency |
|---|---|---|---|---|
| Supervisor LLM | Chat | 5.4 GB | Active | 42ms |
| Code Architect | Code | 8.2 GB | Active | 78ms |
| Watchdog (CPU) | Function | — (CPU) | Active | 12ms |
| Image Diffusion | Visual | 4.8 GB | Idle | — |
| Translation Engine | i18n | 2.4 GB | Unloaded | — |