AMD EPYC Turin vs. Intel Xeon 6 Granite Rapids vs. Graviton4 Benchmarks With AWS M8 Instances

Written by Michael Larabel in Cloud on 24 October 2025 at 11:00 AM EDT. Page 9 of 10. 5 Comments.

👁 TensorFlow benchmark with settings of Device: CPU, Batch Size: 1, Model: ResNet-50. m8a.4xlarge was the fastest.

👁 TensorFlow benchmark with settings of Device: CPU, Batch Size: 256, Model: ResNet-50. m8a.4xlarge was the fastest.

👁 OpenVINO benchmark with settings of Model: Person Detection FP16, Device: CPU. m8a.4xlarge was the fastest.

👁 OpenVINO benchmark with settings of Model: Vehicle Detection FP16, Device: CPU. m8a.4xlarge was the fastest.

👁 OpenVINO benchmark with settings of Model: Face Detection FP16-INT8, Device: CPU. m8a.4xlarge was the fastest.

For those considering the AWS M8 instances for CPU-based AI inferencing, the AMD EPYC Turin powered M8a continued offering the best performance. With the OpenVINO AI toolkit there is support for Advanced Matrix Extensions (AMX) found on Granite Rapids. However, with the m8i.4xlarge instance relying on Hyper Threading to get to 16 vCPUs, AMD EPYC Turin had the upper advantage here still and was coming out with the best value too.

👁 OpenVINO benchmark with settings of Model: Weld Porosity Detection FP16, Device: CPU. m8a.4xlarge was the fastest.

👁 OpenVINO benchmark with settings of Model: Weld Porosity Detection FP16, Device: CPU. m8g.4xlarge was the fastest.

👁 OpenVINO benchmark with settings of Model: Road Segmentation ADAS FP16-INT8, Device: CPU. m8a.4xlarge was the fastest.

5 Comments - Next Page

Page: 1 2 3 4 5 6 7 8 9 10 Next Page

URL: https://www.phoronix.com/review/aws-m8a-m8g-m8i-benchmarks/9

⇱ AMD EPYC Turin vs. Intel Xeon 6 Granite Rapids vs. Graviton4 Benchmarks With AWS M8 Instances Review - Phoronix

AMD EPYC Turin vs. Intel Xeon 6 Granite Rapids vs. Graviton4 Benchmarks With AWS M8 Instances