Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Z.ai (Zhipu)

glm-4.7-flash

Benchmark profile and published results.

Position in the field

Best values compared

Best metrics of this model against the minimum, average and maximum of all published systems.

AMD Radeon RX 7900 XTXAll GPUs
Generation151,7 tok/s
Min 0,1Ø 161,0Max 717,6
Unter dem Durchschnitt · 338 Systeme im Feld
Prefill5.294 tok/s
Min 39Ø 5.997Max 52.503
Unter dem Durchschnitt · 338 Systeme im Feld
Time to First Token1.097 ms
Min 156Ø 18.924Max 354.928
Ueber dem Durchschnitt · 338 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.

GPUby graphics card

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe)AMD Radeon RX 7900 XTXNVIDIA GB10 - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)NVIDIA GB10
AMD Radeon RX 7900 XTX 151,7 tok/sNVIDIA GB10 48,9 tok/s

CPUby processor

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 3955WX 16-Cores - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe)AMD Ryzen Threadrippe...10 x ARM implementer 0x41, part 0xd87 + 10 x ARM implementer 0x41, part 0xd85 - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)10 x ARM implementer ...
AMD Ryzen Threadripper PRO 3955WX 16-Cores 151,7 tok/s10 x ARM implementer 0x41, part 0xd87 + 10 x ARM implementer 0x41, part 0xd85 48,9 tok/s

ENGby engine

18714410056,813,23.4543.7534.0534.353Prefill (tok/s)Generation (tok/s)llama.cpp - 151,7 tok/s Generation, 3.752 tok/s Prefill, TTFT 3.439 ms (3 Laufe)llama.cppvLLM - 48,9 tok/s Generation, 4.055 tok/s Prefill, TTFT 536 ms (1 Lauf)vLLM
llama.cpp 151,7 tok/svLLM 48,9 tok/s
Throughput & latency

Performance benchmark

Metric:
GPUs
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
151,70 tok/s TG
Prefill 5.294 · TTFT 5.865 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAMllama.cppgodclawQ4_K_MDetails →
2glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,06 tok/s TG
Prefill 4.019 · TTFT 3.355 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAMllama.cppgodclawQ4_K_MDetails →
3glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
48,92 tok/s TG
Prefill 4.055 · TTFT 536 ms
1×NVIDIA GB10 (DGX Spark)10 x ARM implementer 0x41, part 0xd87 + 10 x ARM implementer 0x41, part 0xd85 · 120 GB RAMvLLMgodclawAWQDetails →
4glm-4.7-flashZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
43,51 tok/s TG
Prefill 1.942 · TTFT 1.097 ms
1×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAMllama.cppgodclawQ4_K_MDetails →
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.