- AMD’s MI400 press release publishes exactly one performance figure
- 288 TFLOPS of hardware FP64 on the MI430X, a GPU it positions as its go-to for supreme AI and HPC
- Unlike the MI455X, which it launched alongside, the MI430X will have researchers and superior AI clients waiting longer, with AMD targeting early 2027 for its first shipments
AMD has launched its latest Instinct MI400 series, revealing two new chips that bring performance improvements, larger, faster HBM4 memory and a continued promise to support its open source ROCm stack.
While both chips come with 432GB of HBM4 memory, they both have very different uses: the MI455X is AMD’s attempt to dominate AI data centers and run training and inference for frontier models, while the MI430 is positioned as a high-performance compute (HPC) alternative that offers superior precision thanks to being tuned for FP64 superior performance.
Both GPUs are based on AMD’s CNDA 5 architecture, but the MI430X offers FP64 performance that dwarfs both the MI455X and Nvidia’s Rubin-based offerings.
Latest videos fromTechRadar
Frontier AI demand comes first
The launch, which was actually on paper, still showed where AMD’s focus lies: the Instinct MI455X. There’s a simple reason for that: AI data centers prioritize faster FP4 and FP8 performance for most tasks, such as inference, and the MI455X delivers on that front.
AMD is simply responding to market demand by aiming to ship the MI455X first, though it has top AI buyers lined up, both direct and indirect, including the US Department of Energy, Oracle and even the UK government, to name a few.
AMD stated that the MI455X delivers up to 34 times the token throughput of the MI355X at 18 times lower cost, demonstrating a significant upgrade in performance and efficiency. It’s also arguably AMD’s most hyped release to date, even as it continues to catch up to Nvidia’s market dominance in the AI data center space.
The MI455X comes with the recently announced Helios, AMD’s first rack-scale AI system that launched alongside the new Instinct chips. One of these has 72 MI455X GPUs and 18 sixth-generation EPYC server CPUs, configured in a 1:6 ratio per compute node.
The MI430X, on the other hand, seems to be competing specifically to score buyers who demand higher precision, such as science researchers or even government agencies, where correctness is required at the edges and memory limitations apply even with the MI series accelerator’s 432GB HMB4 in play.
“The next generation of AI will span cross-border AI, supreme AI and scientific computing, each requiring infrastructure optimized for its unique requirements,” said Vamsi Boppana, SVP AI at AMD.
“The AMD Instinct MI400 series expands our AI portfolio with purpose-built solutions optimized for the full range of AI and HPC deployments, built on an open software foundation that gives customers the flexibility to innovate at any scale.”
AMD also has a major buyer for the MI455X in its Helios rack-scale form, which will also give it additional exposure for the pre-IPO: Anthropic. The company has agreed to invest $5 billion in the AI giant, with the latter agreeing to deploy 2 GW of AMD’s MI450 accelerators, although its AI head wasn’t exactly thrilled recently by a perceived drop in performance on Claude Code in early 2026.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds.
