AMD Ryzen 7 7700X3D Linux Performance

Written by Michael Larabel in Processors on 16 July 2026 at 09:00 AM EDT. Page 6 of 8. 19 Comments.
OpenVINO benchmark with settings of Model: Face Detection FP16-INT8, Device: CPU, Benchmark Mode: Throughput. Ryzen 9 9950X3D2 was the fastest.
OpenVINO benchmark with settings of Model: Face Detection FP16-INT8, Device: CPU, Benchmark Mode: Latency. Ryzen 9 9950X3D2 was the fastest.

With the AMD Ryzen 7 7700X3D sporting 3D V-Cache and AVX-512, it does work better than the Intel Core Ultra Series 2 Arrow Lake for some CPU-based AI inference workloads.

OpenVINO benchmark with settings of Model: Age Gender Recognition Retail 0013 FP16-INT8, Device: CPU, Benchmark Mode: Throughput. Ryzen 9 9950X3D2 was the fastest.
OpenVINO benchmark with settings of Model: Age Gender Recognition Retail 0013 FP16-INT8, Device: CPU, Benchmark Mode: Latency. Ryzen 7 9800X3D was the fastest.

With just one CCD and 3D V-Cache, the Ryzen 7 7700X3D was working out remarkably well for some of the OpenVINO AI inference benchmarks when it came to the inference latency.

OpenVINO benchmark with settings of Model: Weld Porosity Detection FP16-INT8, Device: CPU, Benchmark Mode: Latency. Ryzen 9 9950X3D2 was the fastest.
OpenVINO benchmark with settings of Model: Road Segmentation ADAS FP16-INT8, Device: CPU, Benchmark Mode: Latency. Ryzen 9 9950X3D2 was the fastest.
OpenVINO benchmark with settings of Model: Noise Suppression Poconet-Like FP16, Device: CPU, Benchmark Mode: Latency. Ryzen 7 9800X3D was the fastest.
Llama.cpp benchmark with settings of Backend: CPU BLAS, Model: gpt-oss-20b-Q8_0, Test: Text Generation 128. Ryzen 9 9900X was the fastest.
Llama.cpp benchmark with settings of Backend: CPU BLAS, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Text Generation 128. Core Ultra 7 270K Plus was the fastest.
Llama.cpp benchmark with settings of Backend: CPU BLAS, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Prompt Processing 512. Ryzen 9 9950X3D2 was the fastest.
Llama.cpp benchmark with settings of Backend: CPU BLAS, Model: GLM-4.7-Flash-IQ4_XS, Test: Text Generation 128. Ryzen 9 9950X3D2 was the fastest.
Llama.cpp benchmark with settings of Backend: CPU BLAS, Model: GLM-4.7-Flash-IQ4_XS, Test: Prompt Processing 512. Ryzen 9 9950X3D2 was the fastest.
Related Articles