LLM Load Balancer

Live worker allocation, throughput, insights, and request analytics across the LM Studio fleet.

Throughput

Now
0req/hr0% errors
5 min
0req/hr0% errors
1 hour
0req/hr0% errors
1 day
0req/hr0% errors
1 week
0req/hr0% errors

Request history

Requests0
Tokens0
Avg tokens/sec0
Error rate %0
Requests by model
Loading…
Requests by worker
Loading…
Tokens/sec by model
Loading…
Model load × throughput
Loading…
Loading errors…

Insights

Today
Top models
No requests yet
Top sources
No attributed sources yet
Top tools
No tool calls yet
Top users
No attributed users yet

Live workers

connecting…
0 jobs running · 0/0 healthy
Waiting for worker data…

Recent requests

TimeModelWorkerLatencySpeedToolsSourceUserStatus
Loading…