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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2411243-PTS-LLAMAFUN93
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Sensor Monitoring

Show Accumulated Sensor Monitoring Data For Displayed Results

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX
November 24
  1 Hour, 30 Minutes
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):


llama funOpenBenchmarking.orgPhoronix Test SuiteAMD 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 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionLlama Fun 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) - 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 - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-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 - Llama-3.1-Tulu-3-8B-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 2048llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-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 - Text Generation 128llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128AMD Ryzen Threadripper 7980X 64-Cores - AMD Radeon RX151.91151.40125.64101.35104.06331.37415.85247.17123.0515.5116.3476.72OpenBenchmarking.org

Llama.cpp

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

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

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

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

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

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

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

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

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

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

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

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