llama

AMD Ryzen 7 7840U testing with a Framework FRANMDCP07 (03.03 BIOS) and AMD Phoenix1 512MB 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 2401119-NE-LLAMA444079
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

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
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
January 11
  9 Minutes
b
January 11
  24 Minutes
c
January 11
  9 Minutes
d
January 11
  8 Minutes
Invert Hiding All Results Option
  12 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 SuiteAMD Ryzen 7 7840U @ 5.13GHz (8 Cores / 16 Threads)Framework FRANMDCP07 (03.03 BIOS)AMD Device 14e82 x 8 GB DRAM-5600MT/s AD5S56008G-B512GB Western Digital WD PC SN740 SDDPNQD-512GAMD Phoenix1 512MB (2700/2800MHz)AMD Rembrandt Radeon HD AudioMEDIATEK MT7922 802.11ax PCIUbuntu 23.106.7.0-060700rc5-generic (x86_64)GNOME Shell 45.1X Server 1.21.1.7 + Wayland4.6 Mesa 24.0~git2312160600.5d937f~oibaf~m (git-5d937f0 2023-12-16 mantic-oibaf-ppa) (LLVM 16.0.6 DRM 3.56)GCC 13.2.0ext42256x1504ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-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: amd-pstate-epp powersave (EPP: 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 + 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 + srbds: Not affected + tsx_async_abort: Not affected

abcdResult OverviewPhoronix Test Suite100%101%101%102%Llama.cppLlama.cppCacheBenchCacheBenchCacheBenchllama-2-13b.Q4_0.ggufllama-2-7b.Q4_0.ggufWriteReadR.M.W

llamacachebench: Readcachebench: Writecachebench: Read / Modify / Writellama-cpp: llama-2-7b.Q4_0.ggufllama-cpp: llama-2-13b.Q4_0.ggufabcd12396.2754872497.856295131556.50111613.327.1112270.09607172913.162070131367.67014213.597.1512319.49822672157.67985130628.2741713.487.1812381.07344772501.828301131333.36296113.57.29OpenBenchmarking.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: Readbcda3K6K9K12K15KSE +/- 18.01, N = 312270.1012319.5012381.0712396.28MIN: 12226.09 / MAX: 12316.73MIN: 12310.3 / MAX: 12325.17MIN: 12375.59 / MAX: 12381.24MIN: 12367.08 / MAX: 12496.621. (CC) gcc options: -O3 -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Writecadb16K32K48K64K80KSE +/- 19.79, N = 372157.6872497.8672501.8372913.16MIN: 71728.42 / MAX: 72349.37MIN: 72039.23 / MAX: 72756.09MIN: 72040.49 / MAX: 72760.16MIN: 72419.43 / MAX: 73142.211. (CC) gcc options: -O3 -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / Writecdba30K60K90K120K150KSE +/- 334.41, N = 3130628.27131333.36131367.67131556.50MIN: 103222.92 / MAX: 141269.42MIN: 105232.15 / MAX: 142024.31MIN: 103002.69 / MAX: 142719.87MIN: 104085.06 / MAX: 142061.031. (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.ggufacdb3691215SE +/- 0.15, N = 313.3213.4813.5013.591. (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.ggufabcd246810SE +/- 0.01, N = 37.117.157.187.291. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas