🖥 AI Server Observability Dashboard
192.168.1.20 · NVIDIA L4 · Ollama · Live monitoring
GPU — NVIDIA L4 (24 GB VRAM)
GPU Utilization
—
VRAM Used
—
GPU Temperature
—
Power Draw
—
Service Health
Ollama API
checking...
GPU Exporter
checking...
Node Exporter
checking...
Models Loaded in VRAM
—
—
VRAM Allocation
Models Loaded in GPU
Loading...
Model Response Tester
Loading models...
Hello! What are you?
▶ Send Test
Latency:
—
Tokens:
—
Tokens/sec:
—
Status:
—
Last updated:
—