dkd AMD Ryzen 7 7840U testing with a Framework Laptop 13 (AMD Ryzen 7040 ) FRANMDCP07 (03.03 BIOS) and GFX1103_R1 512MB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2406037-NE-DKD00122471&sro .
dkd Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c AMD Ryzen 7 7840U @ 5.13GHz (8 Cores / 16 Threads) Framework Laptop 13 (AMD Ryzen 7040 ) FRANMDCP07 (03.03 BIOS) AMD Device 14e8 2 x 8GB DRAM-5600MT/s A-DATA AD5S56008G-B 512GB Western Digital WD PC SN740 SDDPNQD-512G GFX1103_R1 512MB (2700/2800MHz) AMD Device 1640 MEDIATEK Device 0616 Ubuntu 22.04 6.5.0-35-generic (x86_64) GNOME Shell 42.9 X Server + Wayland 4.6 Mesa 23.2.1-1ubuntu3.1~22.04.2 (LLVM 15.0.7 DRM 3.54) 1.3.255 GCC 11.4.0 ext4 2256x1504 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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,brig,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-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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 Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: performance) - Platform Profile: balanced - CPU Microcode: 0xa704103 - ACPI Profile: balanced Security Details - 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
dkd glibc-bench: cos glibc-bench: exp glibc-bench: ffs glibc-bench: pow glibc-bench: sin glibc-bench: log2 glibc-bench: modf glibc-bench: sinh glibc-bench: sqrt glibc-bench: tanh glibc-bench: asinh glibc-bench: atanh glibc-bench: ffsll glibc-bench: sincos glibc-bench: pthread_once perf-bench: Epoll Wait perf-bench: Futex Hash perf-bench: Memcpy 1MB perf-bench: Memset 1MB perf-bench: Sched Pipe perf-bench: Futex Lock-Pi perf-bench: Syscall Basic dav1d: Chimera 1080p dav1d: Summer Nature 4K dav1d: Summer Nature 1080p dav1d: Chimera 1080p 10-bit svt-av1: Preset 3 - Bosphorus 4K svt-av1: Preset 5 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 3 - Bosphorus 1080p svt-av1: Preset 5 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 1080p svt-av1: Preset 13 - Bosphorus 1080p cpuminer-opt: Magi cpuminer-opt: x20r cpuminer-opt: scrypt cpuminer-opt: Deepcoin cpuminer-opt: Ringcoin cpuminer-opt: Blake-2 S cpuminer-opt: Garlicoin cpuminer-opt: Skeincoin cpuminer-opt: Myriad-Groestl cpuminer-opt: LBC, LBRY Credits cpuminer-opt: Quad SHA-256, Pyrite cpuminer-opt: Triple SHA-256, Onecoin whisper-cpp: ggml-base.en - 2016 State of the Union whisper-cpp: ggml-small.en - 2016 State of the Union whisper-cpp: ggml-medium.en - 2016 State of the Union llama-cpp: Meta-Llama-3-8B-Instruct-Q8_0.gguf llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - CPU llamafile: mistral-7b-instruct-v0.2.Q5_K_M - CPU a b c 50.9015 11.0321 4.0534 25.6837 45.5545 7.59953 4.80312 16.708 5.89152 19.4718 16.3723 20.3649 4.09379 28.096 4.06541 133089 3428929 53.936535 118.882768 208589 982 8179538 731.04 235.69 1042.07 593.24 2.96 9.38 26.589 90.533 11.916 37.597 99.031 462.707 265.2 3249 117.88 3511.22 1473 55890 1382.59 17660 4649.35 6707.41 26010 31360 140.60941 418.00075 1254.338 7.1 25.32 10.77 51.1713 11.2133 4.14539 26.0863 45.818 7.70378 4.84911 16.8414 5.94479 19.5643 16.4447 20.4442 4.10287 28.31 4.10783 132922 3446990 54.146143 116.209297 208086 982 8163471 724.15 234.68 1023.3 589.14 2.94 9.296 26.824 93.691 11.874 37.815 98.245 459.689 264.4 3174.84 116.72 3522.22 1404.43 55860 1375.79 17800 4625.74 6703.16 26340 29970 142.68631 419.39169 1257.49788 7.12 27.32 10.77 50.5671 10.9074 4.08667 25.6853 45.3374 7.62419 4.81009 16.5544 5.92854 19.542 16.4235 20.4325 4.11257 28.3249 4.10222 133846 3414551 53.782991 115.937921 205734 982 7828555 730.82 234.19 1041.98 595.45 2.953 9.314 26.624 83.439 11.87 37.894 99.096 459.714 264.89 3167.28 118.21 3527.52 1405.47 55850 1379.71 17730 4653.76 6715.54 26030 31620 141.09938 419.71047 1257.67462 7.11 26.66 10.74 OpenBenchmarking.org
Glibc Benchmarks Benchmark: cos OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: cos a b c 12 24 36 48 60 50.90 51.17 50.57 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: exp OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: exp a b c 3 6 9 12 15 11.03 11.21 10.91 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: ffs OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: ffs a b c 0.9327 1.8654 2.7981 3.7308 4.6635 4.05340 4.14539 4.08667 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: pow OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: pow a b c 6 12 18 24 30 25.68 26.09 25.69 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: sin OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sin a b c 10 20 30 40 50 45.55 45.82 45.34 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: log2 OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: log2 a b c 2 4 6 8 10 7.59953 7.70378 7.62419 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: modf OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: modf a b c 1.091 2.182 3.273 4.364 5.455 4.80312 4.84911 4.81009 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: sinh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sinh a b c 4 8 12 16 20 16.71 16.84 16.55 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: sqrt OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sqrt a b c 1.3376 2.6752 4.0128 5.3504 6.688 5.89152 5.94479 5.92854 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: tanh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: tanh a b c 5 10 15 20 25 19.47 19.56 19.54 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: asinh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: asinh a b c 4 8 12 16 20 16.37 16.44 16.42 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: atanh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: atanh a b c 5 10 15 20 25 20.36 20.44 20.43 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: ffsll OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: ffsll a b c 0.9253 1.8506 2.7759 3.7012 4.6265 4.09379 4.10287 4.11257 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: sincos OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sincos a b c 7 14 21 28 35 28.10 28.31 28.32 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: pthread_once OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: pthread_once a b c 0.9243 1.8486 2.7729 3.6972 4.6215 4.06541 4.10783 4.10222 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
perf-bench Benchmark: Epoll Wait OpenBenchmarking.org ops/sec, More Is Better perf-bench 6.9 Benchmark: Epoll Wait a b c 30K 60K 90K 120K 150K 133089 132922 133846 1. (CXX) g++ options: -MD -std=gnu++17 -fno-exceptions -fno-rtti
perf-bench Benchmark: Futex Hash OpenBenchmarking.org ops/sec, More Is Better perf-bench 6.9 Benchmark: Futex Hash a b c 700K 1400K 2100K 2800K 3500K 3428929 3446990 3414551 1. (CXX) g++ options: -MD -std=gnu++17 -fno-exceptions -fno-rtti
perf-bench Benchmark: Memcpy 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench 6.9 Benchmark: Memcpy 1MB a b c 12 24 36 48 60 53.94 54.15 53.78 1. (CXX) g++ options: -MD -std=gnu++17 -fno-exceptions -fno-rtti
perf-bench Benchmark: Memset 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench 6.9 Benchmark: Memset 1MB a b c 30 60 90 120 150 118.88 116.21 115.94 1. (CXX) g++ options: -MD -std=gnu++17 -fno-exceptions -fno-rtti
perf-bench Benchmark: Sched Pipe OpenBenchmarking.org ops/sec, More Is Better perf-bench 6.9 Benchmark: Sched Pipe a b c 40K 80K 120K 160K 200K 208589 208086 205734 1. (CXX) g++ options: -MD -std=gnu++17 -fno-exceptions -fno-rtti
perf-bench Benchmark: Futex Lock-Pi OpenBenchmarking.org ops/sec, More Is Better perf-bench 6.9 Benchmark: Futex Lock-Pi a b c 200 400 600 800 1000 982 982 982 1. (CXX) g++ options: -MD -std=gnu++17 -fno-exceptions -fno-rtti
perf-bench Benchmark: Syscall Basic OpenBenchmarking.org ops/sec, More Is Better perf-bench 6.9 Benchmark: Syscall Basic a b c 2M 4M 6M 8M 10M 8179538 8163471 7828555 1. (CXX) g++ options: -MD -std=gnu++17 -fno-exceptions -fno-rtti
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Chimera 1080p a b c 160 320 480 640 800 731.04 724.15 730.82 1. (CC) gcc options: -pthread
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Summer Nature 4K a b c 50 100 150 200 250 235.69 234.68 234.19 1. (CC) gcc options: -pthread
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Summer Nature 1080p a b c 200 400 600 800 1000 1042.07 1023.30 1041.98 1. (CC) gcc options: -pthread
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 1.4.2 Video Input: Chimera 1080p 10-bit a b c 130 260 390 520 650 593.24 589.14 595.45 1. (CC) gcc options: -pthread
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 3 - Input: Bosphorus 4K a b c 0.666 1.332 1.998 2.664 3.33 2.960 2.940 2.953 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 5 - Input: Bosphorus 4K a b c 3 6 9 12 15 9.380 9.296 9.314 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b c 6 12 18 24 30 26.59 26.82 26.62 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b c 20 40 60 80 100 90.53 93.69 83.44 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 3 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 3 - Input: Bosphorus 1080p a b c 3 6 9 12 15 11.92 11.87 11.87 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 5 - Input: Bosphorus 1080p a b c 9 18 27 36 45 37.60 37.82 37.89 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b c 20 40 60 80 100 99.03 98.25 99.10 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b c 100 200 300 400 500 462.71 459.69 459.71 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Magi a b c 60 120 180 240 300 265.20 264.40 264.89 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: x20r OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: x20r a b c 700 1400 2100 2800 3500 3249.00 3174.84 3167.28 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: scrypt a b c 30 60 90 120 150 117.88 116.72 118.21 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Deepcoin a b c 800 1600 2400 3200 4000 3511.22 3522.22 3527.52 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Ringcoin a b c 300 600 900 1200 1500 1473.00 1404.43 1405.47 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Blake-2 S a b c 12K 24K 36K 48K 60K 55890 55860 55850 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Garlicoin a b c 300 600 900 1200 1500 1382.59 1375.79 1379.71 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Skeincoin a b c 4K 8K 12K 16K 20K 17660 17800 17730 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Myriad-Groestl a b c 1000 2000 3000 4000 5000 4649.35 4625.74 4653.76 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: LBC, LBRY Credits a b c 1400 2800 4200 5600 7000 6707.41 6703.16 6715.54 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Quad SHA-256, Pyrite a b c 6K 12K 18K 24K 30K 26010 26340 26030 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 24.3 Algorithm: Triple SHA-256, Onecoin a b c 7K 14K 21K 28K 35K 31360 29970 31620 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lgmp
Whisper.cpp Model: ggml-base.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-base.en - Input: 2016 State of the Union a b c 30 60 90 120 150 140.61 142.69 141.10 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
Whisper.cpp Model: ggml-small.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-small.en - Input: 2016 State of the Union a b c 90 180 270 360 450 418.00 419.39 419.71 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
Whisper.cpp Model: ggml-medium.en - Input: 2016 State of the Union OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-medium.en - Input: 2016 State of the Union a b c 300 600 900 1200 1500 1254.34 1257.50 1257.67 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512vnni
Llama.cpp Model: Meta-Llama-3-8B-Instruct-Q8_0.gguf OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b3067 Model: Meta-Llama-3-8B-Instruct-Q8_0.gguf a b c 2 4 6 8 10 7.10 7.12 7.11 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
Llamafile Test: TinyLlama-1.1B-Chat-v1.0.BF16 - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.6 Test: TinyLlama-1.1B-Chat-v1.0.BF16 - Acceleration: CPU a b c 6 12 18 24 30 25.32 27.32 26.66
Llamafile Test: mistral-7b-instruct-v0.2.Q5_K_M - Acceleration: CPU OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.8.6 Test: mistral-7b-instruct-v0.2.Q5_K_M - Acceleration: CPU a b c 3 6 9 12 15 10.77 10.77 10.74
Phoronix Test Suite v10.8.5