Z
Manufacturer
Z.ai (Zhipu)
GLM-Modellfamilie von Z.ai / Zhipu AI.
Best token generation
661,8 tok/s
GLM-4.5-Air
Best prefill
11.803,5 tok/s
GLM-4.5-Air
∅ Token generation
112,5 tok/s
Average of 63 runs
∅ Prefill
1.977,2 tok/s
Average of 63 runs
Best TTFT
407 ms
GLM-4.5-Air
Best harness rate
0%
no harness run yet
🏆
GLM-4.5-Air · fastest model at 661,8 tok/s token generation
Best prefill of this manufacturer: 11.803,5 tok/s (GLM-4.5-Air)
Best prefill of this manufacturer: 11.803,5 tok/s (GLM-4.5-Air)
Top models by token generation
Best measured generation throughput per model (tok/s), published performance benchmarks.