AMD EPYC 8534P

AMD EPYC 8534P 64-Core testing with a AMD Cinnabar (RCB1009C BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2401286-NE-AMDEPYC8520
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

CPU Massive 2 Tests
HPC - High Performance Computing 5 Tests
Large Language Models 2 Tests
Machine Learning 5 Tests
Python Tests 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
January 27
  1 Hour, 30 Minutes
b
January 28
  1 Hour, 29 Minutes
c
January 28
  4 Hours, 26 Minutes
Invert Hiding All Results Option
  2 Hours, 29 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


AMD EPYC 8534POpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads)AMD Cinnabar (RCB1009C BIOS)AMD Device 14a46 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 23.106.5.0-5-generic (x86_64)GNOME ShellX Server 1.21.1.7GCC 13.2.0ext4640x480ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionAMD EPYC 8534P BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-FTCNCZ/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-FTCNCZ/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212 - a: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu1)- Python 3.11.5- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%100%101%101%Llama.cppSVT-AV1SpeedbPyTorchLlamafileQuicksilverTensorFlowY-CruncherNeural Magic DeepSparse

AMD EPYC 8534Pquicksilver: CTS2quicksilver: CORAL2 P1quicksilver: CORAL2 P2svt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080py-cruncher: 1By-cruncher: 500Mpytorch: CPU - 1 - ResNet-50pytorch: CPU - 1 - ResNet-152pytorch: CPU - 16 - ResNet-50pytorch: CPU - 16 - ResNet-152pytorch: CPU - 512 - ResNet-50pytorch: CPU - 512 - ResNet-152pytorch: CPU - 1 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 512 - Efficientnet_v2_ltensorflow: CPU - 1 - ResNet-50tensorflow: CPU - 16 - ResNet-50tensorflow: CPU - 512 - ResNet-50deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamspeedb: Rand Readspeedb: Update Randspeedb: Read While Writingspeedb: Read Rand Write Randllama-cpp: llama-2-7b.Q4_0.ggufllama-cpp: llama-2-13b.Q4_0.ggufllama-cpp: llama-2-70b-chat.Q5_0.ggufllamafile: llava-v1.5-7b-q4 - CPUllamafile: mistral-7b-instruct-v0.2.Q8_0 - CPUllamafile: wizardcoder-python-34b-v1.0.Q6_K - CPUabc1632000021300000162500006.69767.32192.633195.90417.115129.024506.246599.8499.9464.89745.1216.8636.6314.6736.4414.389.386.026.045.9253.65103.335.6549882.432629.640533.72881439.773422.1913202.16314.9412476.836766.9993187.45295.32823766.13018.4779822.751.2115211.5649150.7692151.49126.5945.5826695.375232.161931.0824477.001466.9655187.61995.3237213.5976149.3881151.25236.605313.9872101.6471136.46697.319862.3933508.89344.124222.6415688.567546.406363.983115.614135.5367885.823629.526233.859828770222335526415381020250652827.9516.653.421.9414.275.51636000021330000162600006.7768.423193.581191.92717.63133.524505.536599.429.9154.91445.6016.4436.1314.5537.2814.799.596.046.055.9853.61103.235.6944882.882929.642833.72621441.042122.1797202.11134.9419476.678467.0028187.86945.31683749.03158.5134823.4531.2107212.3922150.1556151.55956.586645.6358694.56332.253430.9938477.282666.9522187.48025.328214.5471148.779152.046.5703313.8012101.7295136.52817.316762.1594512.169943.999622.7036685.106446.641463.703615.681935.6066883.462229.584133.792829844556534551515284219251419627.9416.723.421.8914.295.461629333321316667161933336.72167.778193.425194.47117.565130.345503.508603.5999.9294.91845.3316.5836.6814.6736.7114.559.616.026.035.9453.62103.1935.5891883.114829.575933.80231442.403722.1550198.36915.0360477.056866.9723187.46275.32793754.33728.5026821.13171.2141211.9097150.4754152.14056.560945.5315694.926432.402330.8516477.253166.9459184.65815.4112213.8728149.2086153.93506.4896313.7528101.7894137.01577.291062.1445510.483844.056622.6743685.737346.596364.054615.595835.6474882.972129.631333.739229833220335139415442420250808226.5016.633.4121.9714.275.50OpenBenchmarking.org

Quicksilver

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2abc4M8M12M16M20MSE +/- 8819.17, N = 31632000016360000162933331. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2abc3M6M9M12M15MMin: 16280000 / Avg: 16293333.33 / Max: 163100001. (CXX) g++ options: -fopenmp -O3 -march=native

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1abc5M10M15M20M25MSE +/- 34801.02, N = 32130000021330000213166671. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1abc4M8M12M16M20MMin: 21260000 / Avg: 21316666.67 / Max: 213800001. (CXX) g++ options: -fopenmp -O3 -march=native

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2abc3M6M9M12M15MSE +/- 6666.67, N = 31625000016260000161933331. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2abc3M6M9M12M15MMin: 16180000 / Avg: 16193333.33 / Max: 162000001. (CXX) g++ options: -fopenmp -O3 -march=native

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4Kabc246810SE +/- 0.038, N = 36.6976.7706.7211. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4Kabc3691215Min: 6.68 / Avg: 6.72 / Max: 6.81. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4Kabc1530456075SE +/- 0.17, N = 367.3268.4267.781. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4Kabc1326395265Min: 67.6 / Avg: 67.78 / Max: 68.111. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4Kabc4080120160200SE +/- 2.19, N = 3192.63193.58193.431. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4Kabc4080120160200Min: 190.44 / Avg: 193.42 / Max: 197.691. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4Kabc4080120160200SE +/- 1.23, N = 3195.90191.93194.471. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4Kabc4080120160200Min: 192.16 / Avg: 194.47 / Max: 196.381. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 1080pabc48121620SE +/- 0.16, N = 317.1217.6317.571. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 1080pabc48121620Min: 17.24 / Avg: 17.56 / Max: 17.741. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 1080pabc306090120150SE +/- 1.85, N = 3129.02133.52130.351. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 1080pabc306090120150Min: 126.93 / Avg: 130.35 / Max: 133.271. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 1080pabc110220330440550SE +/- 4.17, N = 3506.25505.54503.511. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 1080pabc90180270360450Min: 496.52 / Avg: 503.51 / Max: 510.941. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 1080pabc130260390520650SE +/- 1.86, N = 3599.85599.42603.601. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 1080pabc110220330440550Min: 601.65 / Avg: 603.6 / Max: 607.311. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1Babc3691215SE +/- 0.006, N = 39.9469.9159.929
OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1Babc3691215Min: 9.92 / Avg: 9.93 / Max: 9.94

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500Mabc1.10662.21323.31984.42645.533SE +/- 0.007, N = 34.8974.9144.918
OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500Mabc246810Min: 4.91 / Avg: 4.92 / Max: 4.93

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50abc1020304050SE +/- 0.20, N = 345.1245.6045.33MIN: 35.13 / MAX: 45.99MIN: 34.79 / MAX: 46.32MIN: 43.73 / MAX: 46.27
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50abc918273645Min: 44.93 / Avg: 45.33 / Max: 45.56

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152abc48121620SE +/- 0.05, N = 316.8616.4416.58MIN: 14.83 / MAX: 17.02MIN: 14.99 / MAX: 16.55MIN: 16.34 / MAX: 16.81
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152abc48121620Min: 16.51 / Avg: 16.58 / Max: 16.69

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50abc816243240SE +/- 0.18, N = 336.6336.1336.68MIN: 35.5 / MAX: 37.04MIN: 34.96 / MAX: 36.54MIN: 30.63 / MAX: 37.51
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50abc816243240Min: 36.43 / Avg: 36.68 / Max: 37.03

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152abc48121620SE +/- 0.08, N = 314.6714.5514.67MIN: 14.48 / MAX: 14.78MIN: 14.35 / MAX: 14.64MIN: 13.21 / MAX: 14.86
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152abc48121620Min: 14.5 / Avg: 14.67 / Max: 14.77

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50abc918273645SE +/- 0.29, N = 336.4437.2836.71MIN: 35.51 / MAX: 36.77MIN: 35.91 / MAX: 37.74MIN: 35.24 / MAX: 37.75
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50abc816243240Min: 36.35 / Avg: 36.71 / Max: 37.28

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152abc48121620SE +/- 0.06, N = 314.3814.7914.55MIN: 12.94 / MAX: 14.47MIN: 13.56 / MAX: 14.89MIN: 13.35 / MAX: 14.76
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152abc48121620Min: 14.46 / Avg: 14.55 / Max: 14.66

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_labc3691215SE +/- 0.04, N = 39.389.599.61MIN: 8.84 / MAX: 9.52MIN: 9.48 / MAX: 9.67MIN: 8.95 / MAX: 9.78
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_labc3691215Min: 9.54 / Avg: 9.61 / Max: 9.67

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_labc246810SE +/- 0.01, N = 36.026.046.02MIN: 5.57 / MAX: 6.13MIN: 5.63 / MAX: 6.16MIN: 5.54 / MAX: 6.14
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_labc246810Min: 6.01 / Avg: 6.02 / Max: 6.04

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_labc246810SE +/- 0.02, N = 36.046.056.03MIN: 5.57 / MAX: 6.16MIN: 5.62 / MAX: 6.16MIN: 5.42 / MAX: 6.21
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_labc246810Min: 5.99 / Avg: 6.03 / Max: 6.06

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: ResNet-50abc1.34552.6914.03655.3826.7275SE +/- 0.04, N = 35.925.985.94
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: ResNet-50abc246810Min: 5.87 / Avg: 5.94 / Max: 5.98

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50abc1224364860SE +/- 0.04, N = 353.6553.6153.62
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50abc1122334455Min: 53.55 / Avg: 53.62 / Max: 53.68

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50abc20406080100SE +/- 0.01, N = 3103.30103.20103.19
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50abc20406080100Min: 103.18 / Avg: 103.19 / Max: 103.2

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc816243240SE +/- 0.02, N = 335.6535.6935.59
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc816243240Min: 35.55 / Avg: 35.59 / Max: 35.63

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc2004006008001000SE +/- 0.36, N = 3882.43882.88883.11
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc150300450600750Min: 882.44 / Avg: 883.11 / Max: 883.66

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc714212835SE +/- 0.02, N = 329.6429.6429.58
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc714212835Min: 29.53 / Avg: 29.58 / Max: 29.6

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc816243240SE +/- 0.03, N = 333.7333.7333.80
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc714212835Min: 33.77 / Avg: 33.8 / Max: 33.86

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc30060090012001500SE +/- 0.78, N = 31439.771441.041442.40
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc30060090012001500Min: 1441.46 / Avg: 1442.4 / Max: 1443.95

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc510152025SE +/- 0.01, N = 322.1922.1822.16
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc510152025Min: 22.13 / Avg: 22.16 / Max: 22.17

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabc4080120160200SE +/- 1.20, N = 3202.16202.11198.37
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabc4080120160200Min: 196.03 / Avg: 198.37 / Max: 200.01

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabc1.13312.26623.39934.53245.6655SE +/- 0.0306, N = 34.94124.94195.0360
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabc246810Min: 4.99 / Avg: 5.04 / Max: 5.1

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabc100200300400500SE +/- 0.22, N = 3476.84476.68477.06
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabc80160240320400Min: 476.83 / Avg: 477.06 / Max: 477.5

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabc1530456075SE +/- 0.04, N = 367.0067.0066.97
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabc1326395265Min: 66.9 / Avg: 66.97 / Max: 67.01

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabc4080120160200SE +/- 0.17, N = 3187.45187.87187.46
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabc306090120150Min: 187.19 / Avg: 187.46 / Max: 187.76

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabc1.19882.39763.59644.79525.994SE +/- 0.0047, N = 35.32825.31685.3279
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabc246810Min: 5.32 / Avg: 5.33 / Max: 5.34

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc8001600240032004000SE +/- 13.07, N = 33766.133749.033754.34
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc7001400210028003500Min: 3728.5 / Avg: 3754.34 / Max: 3770.64

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc246810SE +/- 0.0299, N = 38.47798.51348.5026
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc3691215Min: 8.47 / Avg: 8.5 / Max: 8.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabc2004006008001000SE +/- 1.85, N = 3822.75823.45821.13
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabc140280420560700Min: 818.89 / Avg: 821.13 / Max: 824.8

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabc0.27320.54640.81961.09281.366SE +/- 0.0028, N = 31.21151.21071.2141
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabc246810Min: 1.21 / Avg: 1.21 / Max: 1.22

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc50100150200250SE +/- 0.12, N = 3211.56212.39211.91
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc4080120160200Min: 211.68 / Avg: 211.91 / Max: 212.09

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc306090120150SE +/- 0.10, N = 3150.77150.16150.48
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc306090120150Min: 150.28 / Avg: 150.48 / Max: 150.6

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc306090120150SE +/- 0.03, N = 3151.49151.56152.14
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc306090120150Min: 152.08 / Avg: 152.14 / Max: 152.2

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc246810SE +/- 0.0014, N = 36.59006.58666.5609
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc3691215Min: 6.56 / Avg: 6.56 / Max: 6.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabc1020304050SE +/- 0.07, N = 345.5845.6445.53
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabc918273645Min: 45.38 / Avg: 45.53 / Max: 45.62

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabc150300450600750SE +/- 0.19, N = 3695.38694.56694.93
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabc120240360480600Min: 694.54 / Avg: 694.93 / Max: 695.13

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabc816243240SE +/- 0.02, N = 332.1632.2532.40
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabc714212835Min: 32.36 / Avg: 32.4 / Max: 32.44

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabc714212835SE +/- 0.02, N = 331.0830.9930.85
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabc714212835Min: 30.82 / Avg: 30.85 / Max: 30.9

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc100200300400500SE +/- 0.10, N = 3477.00477.28477.25
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc80160240320400Min: 477.06 / Avg: 477.25 / Max: 477.37

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc1530456075SE +/- 0.02, N = 366.9766.9566.95
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc1326395265Min: 66.92 / Avg: 66.95 / Max: 66.98

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc4080120160200SE +/- 2.60, N = 3187.62187.48184.66
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc306090120150Min: 179.5 / Avg: 184.66 / Max: 187.83

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc1.21752.4353.65254.876.0875SE +/- 0.0772, N = 35.32375.32805.4112
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc246810Min: 5.32 / Avg: 5.41 / Max: 5.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc50100150200250SE +/- 0.26, N = 3213.60214.55213.87
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc4080120160200Min: 213.57 / Avg: 213.87 / Max: 214.38

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc306090120150SE +/- 0.14, N = 3149.39148.78149.21
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc306090120150Min: 148.93 / Avg: 149.21 / Max: 149.41

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabc306090120150SE +/- 0.04, N = 3151.25152.04153.94
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabc306090120150Min: 153.88 / Avg: 153.94 / Max: 154.02

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabc246810SE +/- 0.0019, N = 36.60506.57036.4896
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabc3691215Min: 6.49 / Avg: 6.49 / Max: 6.49

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc70140210280350SE +/- 0.43, N = 3313.99313.80313.75
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc60120180240300Min: 312.9 / Avg: 313.75 / Max: 314.2

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc20406080100SE +/- 0.11, N = 3101.65101.73101.79
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc20406080100Min: 101.67 / Avg: 101.79 / Max: 102.01

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc306090120150SE +/- 0.24, N = 3136.47136.53137.02
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc306090120150Min: 136.76 / Avg: 137.02 / Max: 137.5

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc246810SE +/- 0.0130, N = 37.31987.31677.2910
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc3691215Min: 7.27 / Avg: 7.29 / Max: 7.31

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc1428425670SE +/- 0.16, N = 362.3962.1662.14
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc1224364860Min: 61.84 / Avg: 62.14 / Max: 62.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc110220330440550SE +/- 1.07, N = 3508.89512.17510.48
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc90180270360450Min: 508.57 / Avg: 510.48 / Max: 512.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc1020304050SE +/- 0.05, N = 344.1244.0044.06
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc918273645Min: 43.96 / Avg: 44.06 / Max: 44.12

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc510152025SE +/- 0.02, N = 322.6422.7022.67
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc510152025Min: 22.64 / Avg: 22.67 / Max: 22.72

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc150300450600750SE +/- 1.46, N = 3688.57685.11685.74
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc120240360480600Min: 683.11 / Avg: 685.74 / Max: 688.17

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc1122334455SE +/- 0.10, N = 346.4146.6446.60
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc1020304050Min: 46.43 / Avg: 46.6 / Max: 46.77

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabc1428425670SE +/- 0.14, N = 363.9863.7064.05
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabc1326395265Min: 63.87 / Avg: 64.05 / Max: 64.34

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabc48121620SE +/- 0.03, N = 315.6115.6815.60
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabc48121620Min: 15.53 / Avg: 15.6 / Max: 15.64

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc816243240SE +/- 0.06, N = 335.5435.6135.65
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc816243240Min: 35.58 / Avg: 35.65 / Max: 35.76

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc2004006008001000SE +/- 0.60, N = 3885.82883.46882.97
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc160320480640800Min: 882.04 / Avg: 882.97 / Max: 884.09

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc714212835SE +/- 0.02, N = 329.5329.5829.63
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc714212835Min: 29.59 / Avg: 29.63 / Max: 29.66

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc816243240SE +/- 0.03, N = 333.8633.7933.74
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc714212835Min: 33.71 / Avg: 33.74 / Max: 33.79

Speedb

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Readabc60M120M180M240M300MSE +/- 222389.57, N = 32877022232984455652983322031. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Readabc50M100M150M200M250MMin: 297950238 / Avg: 298332202.67 / Max: 2987205391. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update Randomabc80K160K240K320K400KSE +/- 2346.60, N = 33552643455153513941. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update Randomabc60K120K180K240K300KMin: 346822 / Avg: 351394.33 / Max: 3545971. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While Writingabc3M6M9M12M15MSE +/- 188799.32, N = 31538102015284219154424201. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While Writingabc3M6M9M12M15MMin: 15107795 / Avg: 15442420 / Max: 157612421. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write Randomabc500K1000K1500K2000K2500KSE +/- 12093.31, N = 32506528251419625080821. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write Randomabc400K800K1200K1600K2000KMin: 2486097 / Avg: 2508082 / Max: 25278061. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufabc714212835SE +/- 0.02, N = 327.9527.9426.501. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufabc612182430Min: 26.46 / Avg: 26.5 / Max: 26.531. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufabc48121620SE +/- 0.04, N = 316.6516.7216.631. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufabc48121620Min: 16.56 / Avg: 16.63 / Max: 16.681. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufabc0.76731.53462.30193.06923.8365SE +/- 0.01, N = 33.403.403.411. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufabc246810Min: 3.4 / Avg: 3.41 / Max: 3.421. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUabc510152025SE +/- 0.03, N = 321.9421.8921.97
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUabc510152025Min: 21.94 / Avg: 21.97 / Max: 22.03

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUabc48121620SE +/- 0.02, N = 314.2714.2914.27
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUabc48121620Min: 14.24 / Avg: 14.27 / Max: 14.3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUabc1.23752.4753.71254.956.1875SE +/- 0.02, N = 35.505.465.50
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUabc246810Min: 5.46 / Avg: 5.5 / Max: 5.52

83 Results Shown

Quicksilver:
  CTS2
  CORAL2 P1
  CORAL2 P2
SVT-AV1:
  Preset 4 - Bosphorus 4K
  Preset 8 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
  Preset 4 - Bosphorus 1080p
  Preset 8 - Bosphorus 1080p
  Preset 12 - Bosphorus 1080p
  Preset 13 - Bosphorus 1080p
Y-Cruncher:
  1B
  500M
PyTorch:
  CPU - 1 - ResNet-50
  CPU - 1 - ResNet-152
  CPU - 16 - ResNet-50
  CPU - 16 - ResNet-152
  CPU - 512 - ResNet-50
  CPU - 512 - ResNet-152
  CPU - 1 - Efficientnet_v2_l
  CPU - 16 - Efficientnet_v2_l
  CPU - 512 - Efficientnet_v2_l
TensorFlow:
  CPU - 1 - ResNet-50
  CPU - 16 - ResNet-50
  CPU - 512 - ResNet-50
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  ResNet-50, Baseline - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  ResNet-50, Baseline - Synchronous Single-Stream:
    items/sec
    ms/batch
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  ResNet-50, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    items/sec
    ms/batch
Speedb:
  Rand Read
  Update Rand
  Read While Writing
  Read Rand Write Rand
Llama.cpp:
  llama-2-7b.Q4_0.gguf
  llama-2-13b.Q4_0.gguf
  llama-2-70b-chat.Q5_0.gguf
Llamafile:
  llava-v1.5-7b-q4 - CPU
  mistral-7b-instruct-v0.2.Q8_0 - CPU
  wizardcoder-python-34b-v1.0.Q6_K - CPU