AMD says Instinct MI430X will ship in H1 2027 with 432GB of HBM4
ryanshrout · x · 2026-07-24
AMD says its Instinct MI430X accelerator will ship in H1 2027.
The slide positions it as an "HPC & Sovereign AI Accelerator" and lists several headline specs:
- 288 TFLOPs of HPC FP64 compute, claimed as 8.7× vs. Vera Rubin
- 432 GB of HBM4 memory, a 50% increase vs. Vera Rubin
- 23.3 TB/s of HBM4 bandwidth, up 6% vs. Vera Rubin
Related event: AMD and Anthropic Secure Multi-Billion Dollar AI Partnership(63 posts)→
More from Infra
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27
- Selling a 5090 to scale local inference: one business weighs 5 hardware paths — Anarchaotic · 2026-10-27
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27