llama fun

AMD Ryzen Threadripper 7980X 64-Cores testing with a System76 Thelio Major (FA Z5 BIOS) and AMD Radeon RX 6700 XT 12GB on Ubuntu 24.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2411243-PTS-LLAMAFUN93&grs.

llama funProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RXAMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads)System76 Thelio Major (FA Z5 BIOS)AMD Device 14a44 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA21000GB CT1000T700SSD5AMD Radeon RX 6700 XT 12GBAMD Device 14ccDELL P2415QAquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6EUbuntu 24.046.8.0-48-generic (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 24.0.9-0ubuntu0.2 (LLVM 17.0.6 DRM 3.57)GCC 13.2.0ext41920x1200OpenBenchmarking.org- 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) - CPU Microcode: 0xa108105 - 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: 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

llama funllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048llama-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 512llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048llama-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 512llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-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 512llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX151.40125.64101.3516.34415.85331.37247.1776.72151.91123.05104.0615.51OpenBenchmarking.org

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX306090120150SE +/- 1.25, N = 15151.401. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX306090120150SE +/- 1.22, N = 15125.641. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX20406080100SE +/- 1.28, N = 15101.351. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX48121620SE +/- 0.08, N = 316.341. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX90180270360450SE +/- 3.55, N = 8415.851. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX70140210280350SE +/- 4.15, N = 15331.371. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX50100150200250SE +/- 2.17, N = 15247.171. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX20406080100SE +/- 0.24, N = 576.721. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX306090120150SE +/- 1.39, N = 15151.911. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX306090120150SE +/- 1.50, N = 3123.051. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX20406080100SE +/- 1.41, N = 15104.061. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX48121620SE +/- 0.05, N = 315.511. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Drive Temperature (nvme0n1) Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX918273645Min: 42.85 / Avg: 43.47 / Max: 43.85

Llama.cpp

CPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX1530456075Min: 49.63 / Avg: 67.59 / Max: 75.63

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX9001800270036004500Min: 3718 / Avg: 4213.28 / Max: 5243

Llama.cpp

Drive Temperature (nvme0n1) Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX102030405042.85

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX48.866.581.3OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX225543025341OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX42.943.244.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) Monitor1224364860

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX50.565.073.8OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX234843505338OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX41.943.145.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) Monitor1224364860

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX48.860.066.3OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX336647605339OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX41.942.742.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) Monitor1224364860

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX48.365.773.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX350343245284OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX42.942.943.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) Monitor1224364860

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX47.465.378.8OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX217844045258OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX42.943.843.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) Monitor1224364860

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX47.963.873.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX329644605316OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX102030405043.85

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX50.557.868.1OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX404346005288OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX918273645Min: 41.85 / Avg: 42.56 / Max: 43.85

Llama.cpp

CPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX1632486480Min: 48.25 / Avg: 67.02 / Max: 81.75

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX9001800270036004500Min: 1946 / Avg: 4219.67 / Max: 5274

Llama.cpp

Drive Temperature (nvme0n1) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX40.941.541.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) Monitor1224364860

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX47.964.672.4OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX396543395342OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX39.940.740.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) Monitor1122334455

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX46.063.073.0OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX203043795290OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500

Llama.cpp

Drive Temperature (nvme0n1) Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154Drive Temperature (nvme0n1) MonitorAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX91827364539.85

Llama.cpp

CPU Temperature Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX37.552.761.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b4154CPU Temperature Monitor20406080100

Llama.cpp

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxAMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX390547375280OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b4154CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500


Phoronix Test Suite v10.8.5