
AMD Instinct MI325X - 256GB CDNA3 for Inference
AMD Instinct MI325X specs, benchmarks, and analysis. 256GB HBM3e at 6 TB/s, 2.6 PFLOPS FP8, CDNA3 architecture - the memory-capacity upgrade to the MI300X targeting large model inference.

AMD Instinct MI325X specs, benchmarks, and analysis. 256GB HBM3e at 6 TB/s, 2.6 PFLOPS FP8, CDNA3 architecture - the memory-capacity upgrade to the MI300X targeting large model inference.

AMD's flagship CDNA 4 AI GPU with 432 GB HBM4, 40 PFLOPS FP4, and 2nm chiplet design targeting H2 2026.

AMD expands its Ryzen AI Embedded P100 family with six new 8-to-12-core processors delivering 80 system TOPS, targeting industrial automation, robotics, and medical imaging.

Meta and AMD signed a 6-gigawatt, multi-year GPU pact worth up to $100B - announced days after a separate Nvidia expansion, signaling Meta's deliberate strategy to break single-vendor dependence in AI compute.

Ayar Labs closes a $500M Series E backed by Nvidia, AMD, and Sequoia to mass-produce co-packaged optical interconnects that replace copper in AI data centers.

AMD launches the first desktop processors with Copilot+ qualified NPUs, putting 50 TOPS of on-device AI into AM5 desktops starting Q2 2026.