… 3 Web/App Tier NGINX Server-side Java 4 FFmpeg ~1.00x Requests/Sec ~1.16x Max Ops, multi-instance ~1.23x Frames/Sec 13% Savings 25% Savings 30% Savings Data Tier MySQL Redis ~1.05 Transactions/Min ~1.36 Requests/Sec 17% Savings 36% Savings Confidential VMs Powered by AMD Infinity Guard 5 With AMD I… …
… 3 Web/App Tier Enterprise Applications Web Serving Video Processing Java NGINX FFMPEG 1.6x max-jOPS 1.9x Req/Sec 2.5x Frames/Sec 24% Savings 36% Savings 52% Savings Data Tier SQL Databases Transactional SQL Databases Analytics No SQL Databases MySQL MS SQL Server Redis 1.7x Transactions/min 1.7x Qp… …
… Web Tier App Tier Media Data Tier Web Servicing Caching Enterprise Applications Video Processing Database Analytics Database OLTP Open Source Database OLTP NGINX™ 1 Redis™ 2 Java® 3 FFMPEG 4 SQL Server® TPROC-E 5 SQL Server TPROC-H 6 MySQL TPROC-C 7 ~1.2x Req/Sec ~1.3x Req/Sec ~1.2x max Java OPS ~1… …
… AMD Ryzen™ AI Halo 2,3 GLM 4.7 Flash-30B-A3B +14% GPT-OSS -120B +7% Qwen 3.5-122B-A10B +12% Qwen 3.6-35B-A3B +4% NVIDIA DGX Spark AMD Ryzen AI Halo Performance Tokens/Second NVIDIA DGX Spark Supports Linux Only Lower Tok/Sec per $ No NPU AMD Ryzen AI Halo Supports Windows and Linux OS Leadership … …
… Leadership Performance Insights and Resources The AMD Framework for Secure, Manageable, and Reliable Business PCs A Guide To Evaluating Your Business PC Performance Hardware Security: How Businesses Can Secure Laptops and PCs Featured Systems Powered by AMD Ryzen PRO Desktop Processors Lenovo Think… …
… BMW Group Boosts Security with AMD and Azure BMW Group strengthens identity security and cloud performance by migrating Active Directory to Azure confidential VMs using AMD EPYC™ processors. …
… Customer Success Stories View All Iterate.ai Builds Private AI on AMD Ryzen™ AI PRO Processors Iterate.ai taps AMD Ryzen™ AI PRO processors for 32B private LLMs with 32k context window models at ~60-80 tokens/sec, cutting cloud costs and risks. …
… Image Zoom At 11 nodes and 87 AMD Instinct MI355X GPUs, we delivered 1,042,110 tokens per second in Offline, 1,016,380 tokens per second in Server and 785,522 tokens per second in Interactive. …
… Prompt length tokens TTFT sec TPS tok/sec Memory GB 128 0.54 12.6 13.6 256 0.65 12.5 13.6 512 0.92 12.3 13.7 1024 1.61 11.8 13.8 2048 3.23 10.9 14.0 TTFT – time to first token, TPS – tokens per second Running GPT-OSS-20B with Ryzen AI 1.7 Using ONNX Runtime GenAI 4 , GPT-OSS-20B can be executed loc… …