connecting...
Requests · 72h
--
live from usage ledger
Tokens served
--
across the hive
⚡ Avg speed
--
tokens / second
⏱ p95 latency
--
tail response time
✓ Success rate
--
last 72h
Nodes Online
--
loading...
Total Models
--
available across network
Total VRAM
--
GPU memory pooled
Total RAM
--
memory pooled

🌍 Network Map

0 nodes

🔗 Network Graph

live

📈 Throughput requests + tokens / interval

72h

⏱ Latency p50 vs p95 (ms)

live

🎯 Model Mix by requests

Live Request Stream what the hive is serving right now

--
listening for requests…

⚡ Network Activity

loading activity...