ddda AMD Ryzen AI 9 365 testing with a ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) and AMD Radeon 512MB on Ubuntu 24.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads), Motherboard: ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS), Chipset: AMD Device 1507, Memory: 4 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-026, Disk: 1024GB MTFDKBA1T0QFM-1BD1AABGB, Graphics: AMD Radeon 512MB, Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK Device 7925 OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-phx-eraps (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.59), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 b: Processor: AMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads), Motherboard: ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS), Chipset: AMD Device 1507, Memory: 4 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-026, Disk: 1024GB MTFDKBA1T0QFM-1BD1AABGB, Graphics: AMD Radeon 512MB, Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK Device 7925 OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-phx-eraps (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.59), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 c: Processor: AMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads), Motherboard: ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS), Chipset: AMD Device 1507, Memory: 4 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-026, Disk: 1024GB MTFDKBA1T0QFM-1BD1AABGB, Graphics: AMD Radeon 512MB, Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK Device 7925 OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-phx-eraps (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.59), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 d: Processor: AMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads), Motherboard: ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS), Chipset: AMD Device 1507, Memory: 4 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-026, Disk: 1024GB MTFDKBA1T0QFM-1BD1AABGB, Graphics: AMD Radeon 512MB, Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK Device 7925 OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-phx-eraps (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.59), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 NCNN 20241226 Target: CPU - Model: mobilenet ms < Lower Is Better a . 11.88 |==================================================================== b . 10.73 |============================================================= c . 11.87 |==================================================================== d . 10.51 |============================================================ NCNN 20241226 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 4.68 |===================================================================== b . 4.42 |================================================================= c . 4.47 |================================================================== d . 4.54 |=================================================================== NCNN 20241226 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 3.76 |===================================================================== b . 3.40 |============================================================== c . 3.50 |================================================================ d . 3.51 |================================================================ NCNN 20241226 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better a . 3.23 |===================================================================== b . 3.12 |=================================================================== c . 3.11 |================================================================== d . 3.22 |===================================================================== NCNN 20241226 Target: CPU - Model: mnasnet ms < Lower Is Better a . 3.73 |================================================================= b . 3.99 |===================================================================== c . 3.86 |=================================================================== d . 3.93 |==================================================================== NCNN 20241226 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better a . 5.14 |===================================================================== b . 5.00 |=================================================================== c . 4.97 |=================================================================== d . 4.99 |=================================================================== NCNN 20241226 Target: CPU - Model: blazeface ms < Lower Is Better a . 1.17 |============================================================= b . 1.33 |===================================================================== c . 1.27 |================================================================== d . 1.28 |================================================================== NCNN 20241226 Target: CPU - Model: googlenet ms < Lower Is Better a . 10.22 |================================================================== b . 10.57 |==================================================================== c . 9.49 |============================================================= d . 9.19 |=========================================================== NCNN 20241226 Target: CPU - Model: vgg16 ms < Lower Is Better a . 33.83 |==================================================================== b . 33.42 |=================================================================== c . 32.75 |================================================================== d . 33.19 |=================================================================== NCNN 20241226 Target: CPU - Model: resnet18 ms < Lower Is Better a . 7.05 |===================================================================== b . 5.96 |========================================================== c . 6.12 |============================================================ d . 5.93 |========================================================== NCNN 20241226 Target: CPU - Model: alexnet ms < Lower Is Better a . 5.83 |===================================================================== b . 5.29 |=============================================================== c . 4.97 |=========================================================== d . 5.08 |============================================================ NCNN 20241226 Target: CPU - Model: resnet50 ms < Lower Is Better a . 13.92 |================================================================= b . 14.36 |=================================================================== c . 14.65 |==================================================================== d . 14.44 |=================================================================== NCNN 20241226 Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 ms < Lower Is Better a . 11.88 |==================================================================== b . 10.73 |============================================================= c . 11.87 |==================================================================== d . 10.51 |============================================================ NCNN 20241226 Target: CPU - Model: yolov4-tiny ms < Lower Is Better a . 15.88 |=================================================================== b . 14.69 |============================================================== c . 16.19 |==================================================================== d . 14.85 |============================================================== NCNN 20241226 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better a . 8.44 |================================================================ b . 8.04 |============================================================= c . 9.13 |===================================================================== d . 8.03 |============================================================= NCNN 20241226 Target: CPU - Model: regnety_400m ms < Lower Is Better a . 9.17 |===================================================================== b . 9.19 |===================================================================== c . 9.20 |===================================================================== d . 8.87 |=================================================================== NCNN 20241226 Target: CPU - Model: vision_transformer ms < Lower Is Better a . 70.92 |=================================================================== b . 71.62 |==================================================================== c . 71.61 |==================================================================== d . 71.74 |==================================================================== NCNN 20241226 Target: CPU - Model: FastestDet ms < Lower Is Better a . 4.12 |=================================================================== b . 4.24 |===================================================================== c . 4.17 |==================================================================== d . 4.25 |===================================================================== NCNN 20241226 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better a . 11.39 |================================================================== b . 11.52 |=================================================================== c . 11.51 |=================================================================== d . 11.69 |==================================================================== NCNN 20241226 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 4.34 |===================================================================== b . 4.29 |==================================================================== c . 4.33 |===================================================================== d . 4.32 |===================================================================== NCNN 20241226 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 3.65 |==================================================================== b . 3.56 |=================================================================== c . 3.69 |===================================================================== d . 3.41 |================================================================ NCNN 20241226 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better a . 2.99 |===================================================================== b . 2.82 |================================================================= c . 3.00 |===================================================================== d . 2.91 |=================================================================== NCNN 20241226 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better a . 3.49 |===================================================================== b . 3.41 |=================================================================== c . 3.46 |==================================================================== d . 3.26 |================================================================ NCNN 20241226 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better a . 4.84 |================================================================== b . 4.92 |=================================================================== c . 5.05 |===================================================================== d . 4.80 |================================================================== NCNN 20241226 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better a . 1.24 |===================================================================== b . 1.12 |============================================================== c . 1.19 |================================================================== d . 1.07 |============================================================ NCNN 20241226 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better a . 9.01 |================================================================= b . 9.35 |==================================================================== c . 9.53 |===================================================================== d . 8.74 |=============================================================== NCNN 20241226 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better a . 33.38 |==================================================================== b . 32.29 |================================================================== c . 32.38 |================================================================== d . 33.23 |==================================================================== NCNN 20241226 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better a . 5.97 |============================================================== b . 6.01 |=============================================================== c . 6.60 |===================================================================== d . 6.14 |================================================================ NCNN 20241226 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better a . 4.96 |================================================================= b . 5.04 |================================================================== c . 5.17 |==================================================================== d . 5.23 |===================================================================== NCNN 20241226 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better a . 14.10 |=================================================================== b . 14.00 |================================================================== c . 14.10 |=================================================================== d . 14.38 |==================================================================== NCNN 20241226 Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 ms < Lower Is Better a . 11.39 |================================================================== b . 11.52 |=================================================================== c . 11.51 |=================================================================== d . 11.69 |==================================================================== NCNN 20241226 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better a . 15.18 |============================================================= b . 17.06 |==================================================================== c . 16.17 |================================================================ d . 16.52 |================================================================== NCNN 20241226 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better a . 8.05 |================================================================ b . 8.73 |===================================================================== c . 8.53 |=================================================================== d . 8.31 |================================================================== NCNN 20241226 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better a . 9.12 |===================================================================== b . 8.89 |=================================================================== c . 9.14 |===================================================================== d . 8.74 |================================================================== NCNN 20241226 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better a . 71.32 |=================================================================== b . 71.77 |=================================================================== c . 68.18 |================================================================ d . 72.36 |==================================================================== NCNN 20241226 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better a . 2.77 |================================================ b . 3.49 |============================================================= c . 2.75 |================================================ d . 3.98 |===================================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 10.30 |==================================================================== b . 10.33 |==================================================================== c . 10.32 |==================================================================== d . 10.30 |==================================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 38.71 |==================================================================== b . 37.42 |================================================================== c . 38.40 |=================================================================== d . 37.34 |================================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 37.28 |==================================================================== b . 37.42 |==================================================================== c . 36.94 |=================================================================== d . 37.38 |==================================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 31.62 |============================================================= b . 35.40 |==================================================================== c . 35.16 |==================================================================== d . 32.98 |=============================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 10.75 |=================================================================== b . 10.86 |==================================================================== c . 10.80 |==================================================================== d . 10.81 |==================================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 36.11 |================================================================= b . 37.46 |=================================================================== c . 37.97 |==================================================================== d . 36.32 |================================================================= Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 34.30 |============================================================== b . 37.73 |==================================================================== c . 36.57 |================================================================== d . 35.25 |================================================================ Llama.cpp b4397 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 31.58 |================================================================ b . 33.12 |=================================================================== c . 33.81 |==================================================================== d . 32.63 |================================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 59.22 |================================================================== b . 60.70 |==================================================================== c . 60.75 |==================================================================== d . 58.28 |================================================================= Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 151.41 |================================================================ b . 158.37 |=================================================================== c . 151.53 |================================================================ d . 131.74 |======================================================== Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 151.53 |================================================================ b . 158.82 |=================================================================== c . 150.48 |=============================================================== d . 141.29 |============================================================ Llama.cpp b4397 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 139.28 |================================================================== b . 139.57 |=================================================================== c . 140.36 |=================================================================== d . 139.91 |===================================================================