GET STARTED IN SECONDS
Start monitoring your local AI
Create your account and connect your first Ollama instance.
Continue with Google
or register with work email
Already have an account? Sign in
route What happens after setup:
30s telemetry init1
Install daemon locally
CLI utility
brew install ollama-monitor
2
Auto-detect models running
Target endpoint:
http://localhost:11434
3
Stream real-time performance
Stream sub-millisecond metrics directly to your local HUD or cloud workspace.
OLLAMA HOST SCANNER
3 INSTANCES POLLING
memory
qwen:27b
GPU Ready
VRAM: 15.8 GB • 64.2 tok/s
neurology
llama3.2:3b
Ready
VRAM: 2.1 GB • 118 tok/s
data_object
deepseek-r1:32b
Quantized Q4_K_M
VRAM: 19.4 GB • 42.8 tok/s
AR
“Finally, real-time token tracking without parsing messy stdout strings.”
Alex Rivera
• Principal AI Platform Eng