|
Nemotron-3-Super-120B-A12B-NVFP4 on single DGX Spark: 23.45 tok/s (spark-arena.com/ benhmarks)
|
|
0
|
90
|
May 13, 2026
|
|
Collecting eval results for Spark-sized quants of models
|
|
50
|
1694
|
May 11, 2026
|
|
NIM vs Ollama on RTX 5090: 7.3x Faster Inference + NeMo Guardrails at 2.1% Overhead — 870 Data Points
|
|
0
|
245
|
March 31, 2026
|
|
Request for Approval to Publish DeepStream Benchmarking Results - NMS Layer Placement Analysis
|
|
2
|
63
|
March 16, 2026
|
|
How to benchmark on Thor to get the real FP4/FP8 performance TFOPS
|
|
11
|
454
|
March 16, 2026
|
|
Tools recommended by NVIDIA for measuring DeepStream pipeline performance metrics on Jetson
|
|
5
|
100
|
March 2, 2026
|
|
Benchmarking VLM on Orin
|
|
7
|
300
|
March 2, 2026
|
|
How can I assess general knowledge on a benchmaxxed model?
|
|
1
|
1261
|
February 13, 2026
|
|
Support for openai_gptoss reasoning parser in vLLM, and its impact on the effective inference performance on Spark
|
|
8
|
644
|
February 9, 2026
|
|
How to run MLPerf v3.1 with Thor
|
|
3
|
78
|
January 8, 2026
|
|
What prompt processing speed can one expect above 500k ctx?
|
|
6
|
616
|
January 3, 2026
|
|
Benchmarking and Optimizing Averager algorithm on Jetson Nano
|
|
1
|
93
|
December 14, 2025
|
|
Run hpc_benchmark23.10 HPL with v100GPU
|
|
4
|
1840
|
November 24, 2025
|
|
Clarification on CUDA IPC: Does cudaMemcpyDeviceToDevice guarantee remote memory visibility?
|
|
0
|
58
|
November 13, 2025
|
|
Thor torch.mm benchmark results (float32/float16/float8_e3m2fn)
|
|
5
|
397
|
September 15, 2025
|
|
nVidia nVector - download and documentation
|
|
3
|
3235
|
August 5, 2025
|
|
cuDNN vs cuBLAS performance on GEMMs
|
|
0
|
136
|
June 19, 2025
|
|
Anyone has comparison of LLM engines(TRTLLM/VLLM/MLC)?
|
|
3
|
604
|
June 16, 2025
|
|
Has Anyone Benchmarked (U-Net Segmentation) on Jetson Orin Series?
|
|
2
|
322
|
June 2, 2025
|
|
Source Code of Cutlass GemmKernel from Basic Gemm
|
|
1
|
127
|
April 16, 2025
|
|
Orin nano/nx ResNet-50 benchmark on R36.4.3(jetpack6.2)
|
|
8
|
597
|
March 24, 2025
|
|
Orin nano benchmark on R36.4.3(jetpack6.2)
|
|
14
|
666
|
February 26, 2025
|
|
Issue encountered while executing jetson_benchmarks from GitHub
|
|
3
|
185
|
December 3, 2024
|
|
FPS calculation (estimate) for NVIDIA RTX 2000 Ada Generation Embedded GPU
|
|
0
|
117
|
November 3, 2024
|
|
ONNX engine initialisation/build takes significantly longer in TensorRT 8.5 vs 8.0
|
|
10
|
1683
|
August 20, 2024
|
|
Fp32 precision support on Jetson AGX Orin
|
|
2
|
641
|
June 4, 2024
|
|
Tx2 Benchmarks error
|
|
3
|
335
|
May 21, 2024
|
|
Compare cpu vs gpu execution time with google benchmark
|
|
0
|
614
|
February 15, 2024
|
|
Freeze when running benchmarks
|
|
14
|
1177
|
December 15, 2023
|
|
Jetson Orin Developer Kit - unexpected drop in PCIe transfer speed
|
|
4
|
943
|
December 6, 2023
|