nov Intel Core i7-1280P testing with a MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS) and MSI Intel ADL GT2 8GB on Ubuntu 24.10 via the Phoronix Test Suite. a: Processor: Intel Core i7-1280P @ 4.70GHz (14 Cores / 20 Threads), Motherboard: MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS), Chipset: Intel Alder Lake PCH, Memory: 8 x 2GB LPDDR4-4267MT/s SK Hynix H9HCNNNCPMMLXR-, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: MSI Intel ADL GT2 8GB, Audio: Realtek ALC274, Network: Intel Alder Lake-P PCH CNVi WiFi OS: Ubuntu 24.10, Kernel: 6.11.0-rc6-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: Intel Core i7-1280P @ 4.70GHz (14 Cores / 20 Threads), Motherboard: MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS), Chipset: Intel Alder Lake PCH, Memory: 8 x 2GB LPDDR4-4267MT/s SK Hynix H9HCNNNCPMMLXR-, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: MSI Intel ADL GT2 8GB, Audio: Realtek ALC274, Network: Intel Alder Lake-P PCH CNVi WiFi OS: Ubuntu 24.10, Kernel: 6.11.0-rc6-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1080 bb: Processor: Intel Core i7-1280P @ 4.70GHz (14 Cores / 20 Threads), Motherboard: MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS), Chipset: Intel Alder Lake PCH, Memory: 8 x 2GB LPDDR4-4267MT/s SK Hynix H9HCNNNCPMMLXR-, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: MSI Intel ADL GT2 8GB, Audio: Realtek ALC274, Network: Intel Alder Lake-P PCH CNVi WiFi OS: Ubuntu 24.10, Kernel: 6.11.0-rc6-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: Intel Core i7-1280P @ 4.70GHz (14 Cores / 20 Threads), Motherboard: MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS), Chipset: Intel Alder Lake PCH, Memory: 8 x 2GB LPDDR4-4267MT/s SK Hynix H9HCNNNCPMMLXR-, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: MSI Intel ADL GT2 8GB, Audio: Realtek ALC274, Network: Intel Alder Lake-P PCH CNVi WiFi OS: Ubuntu 24.10, Kernel: 6.11.0-rc6-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1080 Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a .. 13.34 |=================================================================== bb . 13.39 |=================================================================== c .. 9.36 |=============================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a .. 12.48 |============================================================== b .. 13.40 |=================================================================== bb . 13.38 |=================================================================== c .. 9.38 |=============================================== Blender 4.3 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a .. 916.89 |========================================================= b .. 801.74 |================================================= bb . 801.96 |================================================= c .. 1054.24 |================================================================= Blender 4.3 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a .. 755.48 |========================================================== b .. 687.92 |===================================================== bb . 753.66 |========================================================== c .. 864.22 |================================================================== Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256 handshakes/s > Higher Is Better a .. 105546.18 |=========================================================== b .. 111914.76 |=============================================================== bb . 105168.67 |=========================================================== c .. 105132.05 |=========================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a .. 12.77 |============================================================== b .. 13.76 |=================================================================== bb . 13.76 |=================================================================== c .. 7.17 |=================================== Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS13_CHACHA20_POLY1305_SHA256 handshakes/s > Higher Is Better a .. 106054.04 |=========================================================== b .. 112736.73 |=============================================================== bb . 104991.40 |=========================================================== c .. 105650.04 |=========================================================== Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 handshakes/s > Higher Is Better a .. 356237.68 |=========================================================== b .. 379460.51 |=============================================================== bb . 355887.32 |=========================================================== c .. 379788.60 |=============================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a .. 13.70 |=================================================================== b .. 13.79 |=================================================================== bb . 13.77 |=================================================================== c .. 9.59 |=============================================== Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 handshakes/s > Higher Is Better a .. 415559.30 |========================================================== b .. 445443.44 |=============================================================== bb . 416122.79 |========================================================== c .. 448873.55 |=============================================================== Blender 4.3 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a .. 403.53 |=========================================================== b .. 349.60 |=================================================== bb . 399.23 |========================================================== c .. 450.68 |================================================================== Blender 4.3 Blend File: Junkshop - Compute: CPU-Only Seconds < Lower Is Better a .. 368.84 |================================================================== b .. 322.47 |========================================================== bb . 366.21 |================================================================== c .. 355.04 |================================================================ OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token ms < Lower Is Better bb . 222.88 |===================================================== c .. 278.26 |================================================================== OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token ms < Lower Is Better bb . 943.04 |===================================================== c .. 1158.18 |================================================================= ACES DGEMM 1.0 Sustained Floating-Point Rate GFLOP/s > Higher Is Better a .. 179.46 |================================================================= b .. 181.14 |================================================================== bb . 181.33 |================================================================== c .. 180.52 |================================================================== Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 handshakes/s > Higher Is Better a .. 92044.90 |============================================================ b .. 97635.30 |================================================================ bb . 91665.53 |============================================================ c .. 92487.82 |============================================================= Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a .. 13.09 |============================================================== b .. 14.11 |=================================================================== bb . 14.13 |=================================================================== c .. 7.21 |================================== Blender 4.3 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a .. 271.37 |================================================================== b .. 235.55 |========================================================= bb . 270.09 |================================================================== c .. 237.14 |========================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a .. 52.18 |=================================================================== bb . 52.31 |=================================================================== c .. 44.05 |======================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a .. 14.07 |================================================================ b .. 14.82 |=================================================================== bb . 14.10 |================================================================ c .. 9.72 |============================================ Palabos 2.3 Grid Size: 100 Mega Site Updates Per Second > Higher Is Better a .. 43.31 |=================================================================== b .. 40.84 |=============================================================== bb . 26.53 |========================================= c .. 41.19 |================================================================ OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU tokens/s > Higher Is Better bb . 4.49 |==================================================================== c .. 3.59 |====================================================== Rustls 0.23.17 Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256 handshakes/s > Higher Is Better a .. 9355.19 |=========================================================== b .. 10102.42 |================================================================ bb . 9387.98 |=========================================================== c .. 9367.73 |=========================================================== Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 handshakes/s > Higher Is Better a .. 9526.43 |============================================================ b .. 10169.47 |================================================================ bb . 9571.62 |============================================================ c .. 9594.00 |============================================================ Timed Eigen Compilation 3.4.0 Time To Compile Seconds < Lower Is Better a .. 147.80 |================================================================== b .. 148.03 |================================================================== bb . 147.96 |================================================================== c .. 148.04 |================================================================== Palabos 2.3 Grid Size: 400 Mega Site Updates Per Second > Higher Is Better a .. 74.93 |=================================================================== b .. 71.13 |================================================================ bb . 50.73 |============================================= c .. 71.40 |================================================================ Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a .. 6.18 |================================================================= b .. 6.42 |==================================================================== bb . 6.42 |==================================================================== c .. 4.15 |============================================ vkpeak 20240505 int16-vec4 GIOPS > Higher Is Better a .. 1919.65 |================================================================= b .. 1919.43 |================================================================= bb . 1609.56 |======================================================= c .. 1919.40 |================================================================= vkpeak 20240505 int16-scalar GIOPS > Higher Is Better a .. 1013.63 |================================================================= b .. 1013.52 |================================================================= bb . 939.02 |============================================================ c .. 1013.51 |================================================================= vkpeak 20240505 int32-vec4 GIOPS > Higher Is Better a .. 550.78 |================================================================== b .. 550.70 |================================================================== bb . 542.62 |================================================================= c .. 550.72 |================================================================== vkpeak 20240505 int32-scalar GIOPS > Higher Is Better a .. 473.56 |================================================================== b .. 473.51 |================================================================== bb . 473.49 |================================================================== c .. 473.50 |================================================================== vkpeak 20240505 fp16-vec4 GFLOPS > Higher Is Better a .. 3551.69 |================================================================= b .. 3551.19 |================================================================= bb . 3551.00 |================================================================= c .. 3551.16 |================================================================= vkpeak 20240505 fp16-scalar GFLOPS > Higher Is Better a .. 2503.32 |================================================================= b .. 2502.95 |================================================================= bb . 2502.82 |================================================================= c .. 2502.98 |================================================================= vkpeak 20240505 fp32-vec4 GFLOPS > Higher Is Better a .. 1652.72 |================================================================= b .. 1652.47 |================================================================= bb . 1652.35 |================================================================= c .. 1652.46 |================================================================= vkpeak 20240505 fp32-scalar GFLOPS > Higher Is Better a .. 1868.44 |================================================================= b .. 1868.13 |================================================================= bb . 1868.01 |================================================================= c .. 1868.28 |================================================================= OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token ms < Lower Is Better a .. 94.57 |============================================================ bb . 94.78 |============================================================ c .. 104.88 |================================================================== OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token ms < Lower Is Better a .. 191.33 |===================================================== bb . 191.74 |===================================================== c .. 238.24 |================================================================== OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU tokens/s > Higher Is Better a .. 10.57 |=================================================================== bb . 10.55 |=================================================================== c .. 9.53 |============================================================ Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a .. 57.88 |=================================================================== bb . 57.70 |=================================================================== c .. 48.15 |======================================================== Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 handshakes/s > Higher Is Better a .. 809762.81 |=========================================================== b .. 864815.55 |=============================================================== bb . 808705.16 |=========================================================== c .. 811877.86 |=========================================================== Renaissance 0.16 Test: ALS Movie Lens ms < Lower Is Better a .. 14459.4 |============================================================== b .. 15204.0 |================================================================= bb . 14475.6 |============================================================== c .. 14302.4 |============================================================= Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 handshakes/s > Higher Is Better a .. 1082805.90 |========================================================== b .. 1154350.71 |============================================================== bb . 1079421.74 |========================================================== c .. 1083026.43 |========================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a .. 6.60 |==================================================================== bb . 6.60 |==================================================================== c .. 5.09 |==================================================== OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token ms < Lower Is Better a .. 98.98 |====================================================== bb . 100.11 |====================================================== c .. 121.95 |================================================================== OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token ms < Lower Is Better a .. 345.80 |================================================ bb . 335.04 |=============================================== c .. 473.05 |================================================================== OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU tokens/s > Higher Is Better a .. 10.10 |=================================================================== bb . 9.99 |================================================================== c .. 8.20 |====================================================== Renaissance 0.16 Test: In-Memory Database Shootout ms < Lower Is Better a .. 5302.8 |========================================================== b .. 6086.2 |================================================================== bb . 5054.4 |======================================================= c .. 4797.6 |==================================================== Renaissance 0.16 Test: Apache Spark PageRank ms < Lower Is Better a .. 3063.2 |================================================================== b .. 2809.0 |============================================================= bb . 2922.2 |=============================================================== c .. 2815.1 |============================================================= Renaissance 0.16 Test: Akka Unbalanced Cobwebbed Tree ms < Lower Is Better a .. 9185.6 |================================================================== b .. 9157.1 |================================================================== bb . 8669.3 |============================================================== c .. 8570.6 |============================================================== OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a .. 5004.25 |============================================================ b .. 4489.06 |====================================================== bb . 4504.41 |====================================================== c .. 5415.46 |================================================================= OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a .. 1.17 |============================================================= b .. 1.31 |==================================================================== bb . 1.31 |==================================================================== c .. 1.08 |======================================================== Renaissance 0.16 Test: Savina Reactors.IO ms < Lower Is Better a .. 5338.7 |================================================================== b .. 5229.6 |================================================================ bb . 5360.8 |================================================================== c .. 5250.6 |================================================================= Renaissance 0.16 Test: Gaussian Mixture Model ms < Lower Is Better a .. 4643.4 |================================================================== b .. 4581.1 |================================================================= bb . 4616.0 |================================================================== c .. 4534.2 |================================================================ Renaissance 0.16 Test: Finagle HTTP Requests ms < Lower Is Better a .. 4385.9 |================================================================== b .. 3884.6 |========================================================== bb . 4297.2 |================================================================= c .. 3929.9 |=========================================================== Renaissance 0.16 Test: Apache Spark Bayes ms < Lower Is Better a .. 638.2 |====================================================== b .. 745.2 |=============================================================== bb . 716.9 |============================================================= c .. 789.7 |=================================================================== OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a .. 1402.50 |========================================================== b .. 1285.29 |===================================================== bb . 1281.77 |===================================================== c .. 1568.68 |================================================================= OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a .. 4.27 |=============================================================== b .. 4.61 |==================================================================== bb . 4.62 |==================================================================== c .. 3.73 |======================================================= Renaissance 0.16 Test: Random Forest ms < Lower Is Better a .. 570.1 |============================================================= b .. 600.6 |================================================================ bb . 624.2 |=================================================================== c .. 601.9 |================================================================= Renaissance 0.16 Test: Genetic Algorithm Using Jenetics + Futures ms < Lower Is Better a .. 1244.5 |================================================================== b .. 1222.8 |================================================================ bb . 1230.5 |================================================================= c .. 1251.9 |================================================================== Renaissance 0.16 Test: Scala Dotty ms < Lower Is Better a .. 550.0 |============================================================== b .. 561.4 |=============================================================== bb . 596.6 |=================================================================== c .. 573.8 |================================================================ OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a .. 439.61 |================================================================ b .. 411.33 |============================================================ bb . 410.91 |============================================================ c .. 454.25 |================================================================== OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a .. 13.38 |============================================================== b .. 14.53 |=================================================================== bb . 14.57 |=================================================================== c .. 13.01 |============================================================ OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a .. 392.48 |============================================================ b .. 350.74 |====================================================== bb . 352.81 |====================================================== c .. 432.55 |================================================================== OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a .. 15.25 |============================================================ b .. 17.05 |=================================================================== bb . 16.96 |=================================================================== c .. 13.75 |====================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better a .. 259.96 |=============================================================== b .. 246.56 |=========================================================== bb . 240.71 |========================================================== c .. 273.66 |================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better a .. 61.05 |============================================================== b .. 64.71 |================================================================= bb . 66.33 |=================================================================== c .. 58.06 |=========================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better a .. 65.68 |============================================================== b .. 59.62 |======================================================== bb . 59.42 |======================================================== c .. 71.13 |=================================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better a .. 91.10 |============================================================ b .. 100.47 |================================================================== bb . 100.83 |================================================================== c .. 83.92 |======================================================= OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better a .. 238.66 |================================================================= b .. 217.86 |============================================================ bb . 210.75 |========================================================== c .. 241.56 |================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better a .. 66.62 |=========================================================== b .. 73.28 |================================================================= bb . 75.74 |=================================================================== c .. 65.86 |========================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better a .. 117.50 |================================================================= b .. 114.32 |=============================================================== bb . 114.65 |=============================================================== c .. 119.53 |================================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better a .. 50.76 |================================================================= b .. 52.36 |=================================================================== bb . 52.24 |=================================================================== c .. 50.07 |================================================================ OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU ms < Lower Is Better a .. 29.11 |========================================================== b .. 26.71 |===================================================== bb . 26.59 |===================================================== c .. 33.81 |=================================================================== OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU FPS > Higher Is Better a .. 205.02 |============================================================ b .. 223.62 |================================================================== bb . 224.66 |================================================================== c .. 175.67 |==================================================== OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a .. 34.21 |============================================================ b .. 30.68 |====================================================== bb . 30.48 |====================================================== c .. 37.93 |=================================================================== OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a .. 174.78 |=========================================================== b .. 195.02 |================================================================== bb . 196.37 |================================================================== c .. 157.38 |===================================================== OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU ms < Lower Is Better a .. 32.52 |========================================================= b .. 29.42 |==================================================== bb . 29.28 |==================================================== c .. 38.00 |=================================================================== OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU FPS > Higher Is Better a .. 183.94 |=========================================================== b .. 203.39 |================================================================== bb . 204.40 |================================================================== c .. 157.14 |=================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a .. 62.01 |================================================================== b .. 59.37 |=============================================================== bb . 59.87 |================================================================ c .. 63.15 |=================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a .. 96.28 |=============================================================== b .. 100.76 |================================================================== bb . 99.98 |================================================================= c .. 94.65 |============================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better a .. 8.78 |======================================================== b .. 8.15 |==================================================== bb . 8.09 |==================================================== c .. 10.48 |=================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better a .. 678.84 |============================================================= b .. 731.87 |================================================================== bb . 737.31 |================================================================== c .. 565.21 |=================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better a .. 17.79 |============================================================= b .. 16.04 |======================================================= bb . 15.99 |======================================================= c .. 19.39 |=================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better a .. 335.00 |=========================================================== b .. 372.29 |================================================================== bb . 373.56 |================================================================== c .. 306.99 |====================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a .. 1.66 |====================================================== b .. 1.53 |================================================== bb . 1.53 |================================================== c .. 2.08 |==================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a .. 8888.15 |============================================================ b .. 9570.87 |================================================================= bb . 9615.64 |================================================================= c .. 7143.56 |================================================ OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a .. 4.01 |========================================================= b .. 3.63 |==================================================== bb . 3.62 |=================================================== c .. 4.79 |==================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a .. 3750.57 |=========================================================== b .. 4146.33 |================================================================= bb . 4149.86 |================================================================= c .. 3171.54 |================================================== OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token ms < Lower Is Better a .. 44.12 |============================================================= bb . 44.28 |============================================================= c .. 48.81 |=================================================================== OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token ms < Lower Is Better a .. 80.64 |============================================================= bb . 73.03 |======================================================= c .. 88.24 |=================================================================== OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU tokens/s > Higher Is Better a .. 22.66 |=================================================================== bb . 22.58 |=================================================================== c .. 20.49 |============================================================= SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 297 |===================================================================== b .. 296 |===================================================================== bb . 280 |================================================================= c .. 298 |===================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Steady FPS Frames Per Second > Higher Is Better a .. 245 |==================================================================== b .. 248 |===================================================================== bb . 229 |================================================================ c .. 244 |==================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 294 |===================================================================== b .. 286 |=================================================================== bb . 268 |=============================================================== c .. 286 |=================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Steady FPS Frames Per Second > Higher Is Better a .. 245 |===================================================================== b .. 236 |================================================================== bb . 211 |=========================================================== c .. 236 |================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a .. 61.51 |=================================================================== bb . 61.42 |=================================================================== c .. 51.60 |======================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 321 |===================================================================== b .. 318 |==================================================================== bb . 303 |================================================================= c .. 320 |===================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Steady FPS Frames Per Second > Higher Is Better a .. 250 |===================================================================== b .. 151 |========================================== bb . 248 |==================================================================== c .. 251 |===================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 314 |===================================================================== b .. 302 |================================================================== bb . 286 |=============================================================== c .. 307 |=================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Steady FPS Frames Per Second > Higher Is Better a .. 247 |==================================================================== b .. 247 |==================================================================== bb . 236 |================================================================= c .. 252 |===================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 65 |====================================================================== b .. 61 |================================================================== bb . 62 |=================================================================== c .. 63 |==================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Steady FPS Frames Per Second > Higher Is Better a .. 59 |====================================================================== b .. 57 |==================================================================== bb . 55 |================================================================= c .. 57 |==================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 135 |===================================================================== b .. 135 |===================================================================== bb . 131 |=================================================================== c .. 135 |===================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Steady FPS Frames Per Second > Higher Is Better a .. 113 |===================================================================== b .. 46 |============================ bb . 59 |==================================== c .. 47 |============================= SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 60 |====================================================================== b .. 56 |================================================================= bb . 56 |================================================================= c .. 58 |==================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Steady FPS Frames Per Second > Higher Is Better a .. 55 |====================================================================== b .. 51 |================================================================= bb . 50 |================================================================ c .. 52 |================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Mostly Stable FPS Frames Per Second > Higher Is Better a .. 86 |===================================================================== b .. 86 |===================================================================== bb . 81 |================================================================= c .. 87 |====================================================================== SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Steady FPS Frames Per Second > Higher Is Better a .. 76 |====================================================================== b .. 73 |=================================================================== bb . 70 |================================================================ c .. 75 |===================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a .. 28.13 |=================================================================== bb . 28.18 |=================================================================== c .. 23.68 |======================================================== Renaissance 0.16 Test: Apache Spark ALS ms < Lower Is Better