SECURE AUTHENTICATION
Welcome back
Sign in to monitor your Ollama environments.
or continue with email
Don't have an account? Create account
shield
End-to-end local encryption • SOC2 compliant telemetry
localhost:11434
GPU 0 ACTIVE
Ollama Engine Runtime v0.5.11
CUDA 12.4
RTX 4090 • 24GB
Loaded Weight
ONLINE
deepseek-r1:32b
Quantization: Q4_K_M • Size: 19.8GB
VRAM Reserved
4.2 GB
Current Pipeline
STREAMING
38.4
tok/s
POST /api/generate • Latency: 1.42s
Time to First Token
186 ms
GPU Context Allocation
82% / 32,768 ctx
Token Generation Velocity (Last 60s)
Avg 37.1 tok/s
ollama-cli ~ session
$ ollama-monitor auth --verify-session
[OK] Connected to cluster: local-dev-workstation
[OK] 3 instances synced (localhost:11434, node-02:11434, node-edge:11434)
● Telemetry link established via WebSocket (ws://127.0.0.1:9091)