ncnn llama ryzen

AMD Ryzen 7 7840HS testing with a Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS) and AMD Radeon 780M 512MB on Ubuntu 24.04 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 2412296-NE-NCNNLLAMA88
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 29 2024
  1 Hour, 3 Minutes
b
December 29 2024
  1 Hour, 2 Minutes
c
December 29 2024
  1 Hour, 1 Minute
Invert Behavior (Only Show Selected Data)
  1 Hour, 2 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):


ncnn llama ryzenOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads)Framework Laptop 16 (AMD Ryzen 7040 ) FRANMZCP07 (03.01 BIOS)AMD Device 14e82 x 8GB DDR5-5600MT/s A-DATA AD5S56008G-B512GB Western Digital PC SN810 SDCPNRY-512GAMD Radeon 780M 512MBAMD Navi 31 HDMI/DPMEDIATEK MT7922 802.11ax PCIUbuntu 24.046.8.0-49-generic (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 24.2~git2406200600.0ac0fb~oibaf~n (git-0ac0fbc 2024-06-20 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57)GCC 13.2.0ext42560x1600ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionNcnn Llama Ryzen BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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: amd-pstate-epp powersave (EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0xa704103 - ACPI Profile: balanced - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%109%117%126%135%NCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNLlama.cppNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppLlama.cppNCNNLlama.cppLlama.cppNCNNLlama.cppLlama.cppLlama.cppVulkan GPU - resnet18CPU-v2-v2 - mobilenet-v2Vulkan GPU - resnet50Vulkan GPU - googlenetCPU - resnet18CPU - blazefaceVulkan GPU - alexnetCPU - googlenetVulkan GPU - yolov4-tinyCPU - mnasnetCPU - resnet50Vulkan GPU - mnasnetCPU - FastestDetVulkan GPU-v3-v3 - mobilenet-v3Vulkan GPU - squeezenet_ssdVulkan GPU - efficientnet-b0CPU - yolov4-tinyCPU-v3-v3 - mobilenet-v3Vulkan GPU - vgg16CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.5Vulkan GPU - FastestDetVulkan GPU - shufflenet-v2Vulkan GPU - blazefaceCPU - efficientnet-b0Vulkan GPU-v2-v2 - mobilenet-v2CPU - squeezenet_ssdCPU - alexnetVulkan GPU - mobilenetV.G.y.y - mobilenetv2-yolov3CPU - shufflenet-v2CPU - mobilenetCPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3CPU - vgg16Vulkan GPU - regnety_400mCPU - regnety_400mCPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.2CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.1CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.5CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.2CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.5CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.1Vulkan GPU - vision_transformerCPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.2CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - T.G.1CPU - vision_transformerCPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.1CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - T.G.1CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - T.G.1

ncnn llama ryzenncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048abc10.423.012.962.52.814.290.858.5741.136.445.5413.9610.4216.697.216.0759.712.6710.453.032.982.522.814.330.798.7641.346.515.5613.9610.4516.727.316.0960.182.857.1740.5539.937.657.639.5839.5938.2753.66165.04162.78148.119.954.012.752.382.554.030.747.6339.55.525.2312.719.9515.586.835.9359.952.839.892.852.772.372.564.020.747.541.734.914.8715.329.8915.326.965.8659.622.917.2140.0639.7138.547.640.239.5438.5953.55158.7160.59151.489.94.022.752.372.554.020.747.6139.645.475.2312.729.915.476.85.8859.942.599.972.872.752.362.594.010.747.4438.854.834.9112.199.9715.116.765.8559.852.727.2140.5740.1138.747.5940.5639.4938.553.55170.43164.58149.08OpenBenchmarking.org

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: mobilenetabc369121510.429.959.90MIN: 10.34 / MAX: 12.33MIN: 9.85 / MAX: 14.03MIN: 9.78 / MAX: 14.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU-v2-v2 - Model: mobilenet-v2abc0.90451.8092.71353.6184.52253.014.014.02MIN: 2.94 / MAX: 6.3MIN: 2.79 / MAX: 226.32MIN: 2.79 / MAX: 226.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU-v3-v3 - Model: mobilenet-v3abc0.6661.3321.9982.6643.332.962.752.75MIN: 2.9 / MAX: 5.75MIN: 2.67 / MAX: 5.61MIN: 2.67 / MAX: 5.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: shufflenet-v2abc0.56251.1251.68752.252.81252.502.382.37MIN: 2.46 / MAX: 4.33MIN: 2.33 / MAX: 4.92MIN: 2.31 / MAX: 5.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: mnasnetabc0.63231.26461.89692.52923.16152.812.552.55MIN: 2.73 / MAX: 5.32MIN: 2.49 / MAX: 5.11MIN: 2.48 / MAX: 5.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: efficientnet-b0abc0.96531.93062.89593.86124.82654.294.034.02MIN: 4.18 / MAX: 6.88MIN: 3.95 / MAX: 6.79MIN: 3.91 / MAX: 6.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: blazefaceabc0.19130.38260.57390.76520.95650.850.740.74MIN: 0.78 / MAX: 10.11MIN: 0.73 / MAX: 0.92MIN: 0.73 / MAX: 0.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: googlenetabc2468108.577.637.61MIN: 8.44 / MAX: 11.96MIN: 7.51 / MAX: 11MIN: 7.5 / MAX: 9.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: vgg16abc91827364541.1339.5039.64MIN: 40.58 / MAX: 49.94MIN: 38.97 / MAX: 48.87MIN: 39.2 / MAX: 50.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: resnet18abc2468106.445.525.47MIN: 6.37 / MAX: 9.26MIN: 5.42 / MAX: 7.18MIN: 5.38 / MAX: 7.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: alexnetabc1.24652.4933.73954.9866.23255.545.235.23MIN: 5.5 / MAX: 6.96MIN: 5.15 / MAX: 6.92MIN: 5.17 / MAX: 6.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: resnet50abc4812162013.9612.7112.72MIN: 13.83 / MAX: 16.06MIN: 12.57 / MAX: 17.48MIN: 12.59 / MAX: 15.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3abc369121510.429.959.90MIN: 10.34 / MAX: 12.33MIN: 9.85 / MAX: 14.03MIN: 9.78 / MAX: 14.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: yolov4-tinyabc4812162016.6915.5815.47MIN: 16.45 / MAX: 20.64MIN: 15.32 / MAX: 34.14MIN: 15.25 / MAX: 18.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: squeezenet_ssdabc2468107.216.836.80MIN: 7.1 / MAX: 9.12MIN: 6.69 / MAX: 11.01MIN: 6.68 / MAX: 11.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: regnety_400mabc2468106.075.935.88MIN: 5.98 / MAX: 10.09MIN: 5.81 / MAX: 15.99MIN: 5.8 / MAX: 14.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: vision_transformerabc132639526559.7159.9559.94MIN: 58.71 / MAX: 68.89MIN: 59.31 / MAX: 77.78MIN: 58.92 / MAX: 78.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: FastestDetabc0.63681.27361.91042.54723.1842.672.832.59MIN: 2.64 / MAX: 4.2MIN: 2.78 / MAX: 7.44MIN: 2.56 / MAX: 3.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: mobilenetabc369121510.459.899.97MIN: 10.39 / MAX: 10.87MIN: 9.79 / MAX: 12.12MIN: 9.83 / MAX: 13.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2abc0.68181.36362.04542.72723.4093.032.852.87MIN: 2.95 / MAX: 5.6MIN: 2.79 / MAX: 5.37MIN: 2.79 / MAX: 5.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3abc0.67051.3412.01152.6823.35252.982.772.75MIN: 2.92 / MAX: 5.52MIN: 2.68 / MAX: 5.24MIN: 2.69 / MAX: 5.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: shufflenet-v2abc0.5671.1341.7012.2682.8352.522.372.36MIN: 2.47 / MAX: 4.97MIN: 2.32 / MAX: 4.75MIN: 2.29 / MAX: 5.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: mnasnetabc0.63231.26461.89692.52923.16152.812.562.59MIN: 2.74 / MAX: 5.35MIN: 2.5 / MAX: 5.05MIN: 2.49 / MAX: 12.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: efficientnet-b0abc0.97431.94862.92293.89724.87154.334.024.01MIN: 4.2 / MAX: 13.97MIN: 3.93 / MAX: 6.78MIN: 3.92 / MAX: 6.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: blazefaceabc0.17780.35560.53340.71120.8890.790.740.74MAX: 0.85MIN: 0.73 / MAX: 0.82MIN: 0.73 / MAX: 0.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: googlenetabc2468108.767.507.44MIN: 8.51 / MAX: 17.3MIN: 7.37 / MAX: 9.08MIN: 7.32 / MAX: 9.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: vgg16abc102030405041.3441.7338.85MIN: 40.71 / MAX: 55.66MIN: 38.44 / MAX: 161MIN: 38.52 / MAX: 49.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: resnet18abc2468106.514.914.83MIN: 6.4 / MAX: 10.78MIN: 4.82 / MAX: 10.58MIN: 4.76 / MAX: 5.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: alexnetabc1.2512.5023.7535.0046.2555.564.874.91MIN: 5.47 / MAX: 7.38MIN: 4.77 / MAX: 8.68MIN: 4.82 / MAX: 6.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: resnet50abc4812162013.9615.3212.19MIN: 13.81 / MAX: 18.95MIN: 12.54 / MAX: 83.28MIN: 12.08 / MAX: 13.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3abc369121510.459.899.97MIN: 10.39 / MAX: 10.87MIN: 9.79 / MAX: 12.12MIN: 9.83 / MAX: 13.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: yolov4-tinyabc4812162016.7215.3215.11MIN: 16.58 / MAX: 20.56MIN: 15.1 / MAX: 19.94MIN: 14.91 / MAX: 16.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: squeezenet_ssdabc2468107.316.966.76MIN: 7.2 / MAX: 11.67MIN: 6.83 / MAX: 8.76MIN: 6.63 / MAX: 8.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: regnety_400mabc2468106.095.865.85MIN: 6.04 / MAX: 7.35MIN: 5.79 / MAX: 7.35MIN: 5.77 / MAX: 9.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: vision_transformerabc132639526560.1859.6259.85MIN: 58.25 / MAX: 98.64MIN: 58.53 / MAX: 68.86MIN: 58.6 / MAX: 81.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: FastestDetabc0.65481.30961.96442.61923.2742.852.912.72MIN: 2.82 / MAX: 4.26MIN: 2.87 / MAX: 6.78MIN: 2.69 / MAX: 4.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128abc2468107.177.217.211. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512abc91827364540.5540.0640.571. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024abc91827364539.9039.7140.111. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048abc91827364537.6538.5438.741. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128abc2468107.607.607.591. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512abc91827364539.5840.2040.561. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024abc91827364539.5939.5439.491. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048abc91827364538.2738.5938.501. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128abc122436486053.6653.5553.551. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512abc4080120160200165.04158.70170.431. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024abc4080120160200162.78160.59164.581. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048abc306090120150148.11151.48149.081. (CXX) g++ options: -O3

48 Results Shown

NCNN:
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3
  CPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - regnety_400m
  CPU - vision_transformer
  CPU - FastestDet
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - regnety_400m
  Vulkan GPU - vision_transformer
  Vulkan GPU - FastestDet
Llama.cpp:
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048