NanoMind · 152M

Live

Throughput

—

Latency

—

TTFT —

Tokens out—

Throughput History

Session avg—

Peak —

Session

Turns 0

Total tokens0

Server RAM 0

Engine

Server RAM —

Status —

Sessions—

Uptime —

5 phases · cold/warm TTFT · throughput · concurrency

Run benchmark to measure
real system performance

NanoMind · 152M

Chat

Idle

Enter ↵ to send · Shift+Enter for newline