glm-5.2 tokens per second

Live benchmark data for glm-5.2 on ollama. Speed, latency, and reliability — benchmarked every ~10 minutes.

Latest TPS
75.2 tok/s
24h avg TPS
110.1 tok/s
TTFT
848ms
24h reliability
100%
Last tested
47s ago

Tokens per second over time

Time to first token over time

Speed is measured as output tokens ÷ generation time. Each benchmark fires one streaming chat completion with a fixed ~300-token prompt, every ~10 minutes. Full methodology →