llama

Intel Core i9-14900K testing with a ASUS PRIME Z790-P WIFI (1402 BIOS) and Intel Arc A770 DG2 16GB 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 2401115-PTS-LLAMA41637
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
January 11
  24 Minutes
v
January 11
  43 Minutes
c
January 11
  42 Minutes
d
January 11
  24 Minutes
Invert Behavior (Only Show Selected Data)
  33 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):


llamaOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-14900K @ 5.70GHz (24 Cores / 32 Threads)ASUS PRIME Z790-P WIFI (1402 BIOS)Intel Device 7a272 x 16 GB DRAM-6000MT/s Corsair CMK32GX5M2B6000C36Western Digital WD_BLACK SN850X 1000GBIntel Arc A770 DG2 16GB (2400MHz)Realtek ALC897ASUS VP28UUbuntu 23.106.7.0-060700rc7daily20231224-generic (x86_64)GNOME Shell 45.1X Server 1.21.1.74.6 Mesa 24.0~git2312240600.c05261~oibaf~m (git-c05261a 2023-12-24 mantic-oibaf-ppa)OpenCL 3.0GCC 13.2.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionLlama 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-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/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: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x11d - Thermald 2.5.4- 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: Not affected + 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 RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

avcdResult OverviewPhoronix Test Suite100%102%103%105%CacheBenchCacheBenchLlama.cppLlama.cppCacheBenchR.M.WReadllama-2-7b.Q4_0.ggufllama-2-13b.Q4_0.ggufWrite

llamacachebench: Readcachebench: Writecachebench: Read / Modify / Writellama-cpp: llama-2-7b.Q4_0.ggufllama-cpp: llama-2-13b.Q4_0.ggufavcd22912.673526161363.477243176235.84600116.388.7522911.469477161285.203466166291.19254816.448.7522594.465007161299.013930175404.26475716.608.7722913.708604161353.744637175929.32131516.508.76OpenBenchmarking.org

CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Readavcd5K10K15K20K25KSE +/- 0.19, N = 3SE +/- 1.01, N = 3SE +/- 318.35, N = 12SE +/- 0.19, N = 322912.6722911.4722594.4722913.71MIN: 22908.26 / MAX: 22913.68MIN: 22878.67 / MAX: 22914.42MIN: 19091.54 / MAX: 22915.61MIN: 22911.85 / MAX: 22915.861. (CC) gcc options: -O3 -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Writeavcd30K60K90K120K150KSE +/- 125.82, N = 3SE +/- 51.54, N = 3SE +/- 56.50, N = 3SE +/- 71.53, N = 3161363.48161285.20161299.01161353.74MIN: 86690.74 / MAX: 183302.05MIN: 86701.91 / MAX: 183314.99MIN: 86743.71 / MAX: 183256.07MIN: 86730.26 / MAX: 183303.091. (CC) gcc options: -O3 -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / Writeavcd40K80K120K160K200KSE +/- 186.19, N = 3SE +/- 4161.43, N = 12SE +/- 718.69, N = 3SE +/- 161.29, N = 3176235.85166291.19175404.26175929.32MIN: 136248.93 / MAX: 201568.94MIN: 111634.31 / MAX: 201391.75MIN: 128368.83 / MAX: 201388.28MIN: 133100.03 / MAX: 201497.561. (CC) gcc options: -O3 -lrt

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufavcd48121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 316.3816.4416.6016.501. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufavcd246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 38.758.758.778.761. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas