Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DeepReinforce

Ornith-1.5-35B-A3B35B

Benchmark profile and published results.

MoE35B
Position in the field

Best values compared

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

Generation626,4 tok/s
Min 5,0Ø 249,4Max 1.568,0
Ueber dem Durchschnitt · 1028 Systeme im Feld
Prefill28.681 tok/s
Min 94Ø 8.413Max 55.260
Ueber dem Durchschnitt · 1028 Systeme im Feld
Time to First Token245 ms
Min 117Ø 5.305Max 124.920
Ueber dem Durchschnitt · 1028 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

77159642124670,61.4044.5697.73410.899Prefill (tok/s)Generation (tok/s)NVIDIA RTX A6000 - 626,4 tok/s Generation, 9.235 tok/s Prefill, TTFT 2.559 ms (18 Laufe)NVIDIA RTX A6000AMD Radeon AI PRO R9700 - 215,5 tok/s Generation, 3.068 tok/s Prefill, TTFT 3.329 ms (3 Laufe)AMD Radeon AI PRO R97...
NVIDIA RTX A6000 626,4 tok/sAMD Radeon AI PRO R9700 215,5 tok/s

CPUby processor

77159642124670,61.4044.5697.73410.899Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 626,4 tok/s Generation, 9.235 tok/s Prefill, TTFT 2.559 ms (18 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 3 3100 4-Core Processor - 215,5 tok/s Generation, 3.068 tok/s Prefill, TTFT 3.329 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 626,4 tok/sAMD Ryzen 3 3100 4-Core Processor 215,5 tok/s

ENGby engine

6946546155765366867.81114.93722.062Prefill (tok/s)Generation (tok/s)vLLM - 626,4 tok/s Generation, 18.420 tok/s Prefill, TTFT 609 ms (6 Laufe)vLLMllama.cpp - 603,7 tok/s Generation, 4.328 tok/s Prefill, TTFT 3.492 ms (15 Laufe)llama.cpp
vLLM 626,4 tok/sllama.cpp 603,7 tok/s
Throughput & latency

Performance benchmark

Metric:
GPUs
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
626,41 tok/s TG
Prefill 28.681 · TTFT 928 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
2Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
603,66 tok/s TG
Prefill 5.250 · TTFT 7.504 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
3Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
600,91 tok/s TG
Prefill 5.037 · TTFT 7.660 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
4Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
588,56 tok/s TG
Prefill 25.569 · TTFT 1.053 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
5Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
469,63 tok/s TG
Prefill 5.251 · TTFT 8.721 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
6Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
469,10 tok/s TG
Prefill 5.207 · TTFT 8.770 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
7Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
418,21 tok/s TG
Prefill 21.951 · TTFT 535 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
8Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
391,05 tok/s TG
Prefill 19.044 · TTFT 619 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
9Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
259,04 tok/s TG
Prefill 5.008 · TTFT 1.926 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
10Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
256,43 tok/s TG
Prefill 4.992 · TTFT 1.933 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
11Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
215,46 tok/s TG
Prefill 3.907 · TTFT 5.778 ms
10×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M
12Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
210,69 tok/s TG
Prefill 5.070 · TTFT 1.901 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
13Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
209,15 tok/s TG
Prefill 5.053 · TTFT 1.909 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
14Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
166,21 tok/s TG
Prefill 2.966 · TTFT 3.382 ms
5×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M
15Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
159,36 tok/s TG
Prefill 3.711 · TTFT 519 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
16Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
159,15 tok/s TG
Prefill 3.734 · TTFT 517 ms
1×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
17Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
152,55 tok/s TG
Prefill 8.176 · TTFT 245 ms
1×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
18Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
139,18 tok/s TG
Prefill 7.100 · TTFT 278 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
19Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
125,55 tok/s TG
Prefill 3.700 · TTFT 521 ms
1×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
20Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
125,54 tok/s TG
Prefill 3.698 · TTFT 522 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ8_0
21Ornith-1.5-35B-A3B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,10 tok/s TG
Prefill 2.330 · TTFT 828 ms
1×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.