GPU Utilization
GPU—
Streaming multiprocessor load
Local LLM infrastructure
Local LLM · live node telemetry
CONNECTING
VRAM Used / Total
Memory—
GPU allocation in gigabytes
GPU Temperature
Thermal—
Core temperature
Tokens / s
Generation—
Across all model endpoints
Network Throughput
In / Out—
Purple: inbound · cyan dashed: outbound
Throughput
Requests—
Completed requests per second
◎
—
ForgeNode service status
Checking service
↗
—
Total completed requests
Loading metrics
◈
—
Models currently available
Loading inventory