Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
NVIDIA

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120B

Benchmark profile and published results.

MoE120B
Position in the field

Best values compared

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

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAll GPUs
Generation1.562,3 tok/s
Min 7,0Ø 556,8Max 2.143,6
Ueber dem Durchschnitt · 542 Systeme im Feld
Prefill2.593 tok/s
Min 28Ø 6.400Max 43.711
Unter dem Durchschnitt · 533 Systeme im Feld
Time to First Token2.121 ms
Min 59Ø 9.098Max 168.314
Ueber dem Durchschnitt · 542 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

2.0151.5111.0075040,01.7572.2192.6813.144Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.562,3 tok/s Generation, 2.065 tok/s Prefill, TTFT 17.642 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GB10 - 79,8 tok/s Generation, 2.835 tok/s Prefill, TTFT 3.577 ms (3 Laufe)NVIDIA GB10
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.562,3 tok/sNVIDIA GB10 79,8 tok/s

CPUby processor

2.0151.5111.0075040,01.7572.2192.6813.144Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 7945HX with Radeon Graphics - 1.562,3 tok/s Generation, 2.065 tok/s Prefill, TTFT 17.642 ms (3 Laufe)AMD Ryzen 9 7945HX wi...NVIDIA Grace - 79,8 tok/s Generation, 2.835 tok/s Prefill, TTFT 3.577 ms (3 Laufe)NVIDIA Grace
AMD Ryzen 9 7945HX with Radeon Graphics 1.562,3 tok/sNVIDIA Grace 79,8 tok/s

ENGby engine

1.7181.6401.5621.4841.4062.3032.4012.4992.597Prefill (tok/s)Generation (tok/s)vLLM - 1.562,3 tok/s Generation, 2.450 tok/s Prefill, TTFT 10.610 ms (6 Laufe)vLLM
vLLM 1.562,3 tok/s
Throughput & latency

Performance benchmark

Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.562,27 tok/s TG
Prefill 2.593 · TTFT 34.854 ms
10×NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMvLLMgodclawNVFP4Details →
2NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
795,03 tok/s TG
Prefill 2.378 · TTFT 15.951 ms
5×NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMvLLMgodclawNVFP4Details →
3NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
158,32 tok/s TG
Prefill 1.225 · TTFT 2.121 ms
1×NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMvLLMgodclawNVFP4Details →
4NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
79,84 tok/s TG
Prefill 3.760 · TTFT 5.878 ms
10×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMvLLMgodclawNVFP4Details →
5NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
54,14 tok/s TG
Prefill 3.027 · TTFT 3.561 ms
5×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMvLLMgodclawNVFP4Details →
6NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
20,44 tok/s TG
Prefill 1.717 · TTFT 1.294 ms
1×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMvLLMgodclawNVFP4Details →
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.