Z.ai (Zhipu)
glm-5.2-colibri744B
Benchmark profile and published results.
MoE744B
Position in the field
Best values compared
Best metrics of this model against the minimum, average and maximum of all published systems.
Generation0,0 tok/s
Min 0,0Ø 587,1Max 2.414,4
Unter dem Durchschnitt · 57 Systeme im Feld
Prefill211 tok/s
Min 7Ø 14.401Max 39.029
Unter dem Durchschnitt · 57 Systeme im Feld
Time to First Token10.088 ms
Min 114Ø 11.998Max 354.674
Ueber dem Durchschnitt · 57 Systeme im Feld
Performance profile
Throughput by hardware & engine
Each bubble is a GPU, CPU or engine – position shows prompt processing (X) and output speed (Y), bubble size the number of runs.
Throughput & latency
Performance benchmark
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 7 · TTFT 354.674 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | colibricolibriINT4 | Details → | |
| 2 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 211 · TTFT 10.088 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | colibricolibriINT4 | Details → | |
| 3 | glm-5.2-colibri744BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 10 · TTFT 239.030 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | colibri | Details → |
Agent & chat rating
Harness benchmark
Noch keine Harnessbenchmarks fuer dieses Modell.