tr lamma

AMD Ryzen Threadripper 7980X 64-Cores testing with a ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS) and AMD Radeon RX 7900 XT 20GB 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 2401105-PTS-TRLAMMA345
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

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
  10 Minutes
b
January 11
  9 Minutes
c
January 11
  13 Minutes
d
January 11
  4 Minutes
Invert Hiding All Results Option
  9 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):


tr lammaOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 7980X 64-Cores @ 8.21GHz (64 Cores / 128 Threads)ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS)AMD Device 14a4128GB2000GB Corsair MP700 PRO + 1000GB Western Digital WDS100T1X0E-00AFY0AMD Radeon RX 7900 XT 20GB (2025/1249MHz)Realtek ALC1220DELL U2723QEAquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCIUbuntu 23.106.7.0-060700rc2daily20231126-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.7 + Wayland4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.56)GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionTr Lamma 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: 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 + 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

abcdResult OverviewPhoronix Test Suite100%101%103%104%Llama.cppLlama.cppLlama.cppllama-2-7b.Q4_0.ggufllama-2-13b.Q4_0.ggufllama-2-70b-chat.Q5_0.gguf

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.ggufabcd816243240SE +/- 0.43, N = 3SE +/- 0.15, N = 3SE +/- 0.23, N = 1531.2930.7931.2132.551. (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.ggufabcd714212835Min: 30.76 / Avg: 31.29 / Max: 32.15Min: 30.53 / Avg: 30.79 / Max: 31.04Min: 30.44 / Avg: 31.21 / Max: 32.721. (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.ggufabcd510152025SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 318.2418.3218.1818.541. (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.ggufabcd510152025Min: 18.12 / Avg: 18.24 / Max: 18.31Min: 18.23 / Avg: 18.32 / Max: 18.38Min: 18.11 / Avg: 18.18 / Max: 18.211. (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.ggufabcd0.78981.57962.36943.15923.949SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.463.473.483.511. (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.ggufabcd246810Min: 3.45 / Avg: 3.46 / Max: 3.47Min: 3.45 / Avg: 3.47 / Max: 3.48Min: 3.45 / Avg: 3.48 / Max: 3.521. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas