NVIDIA Blackwell
NVL72 rack-scale coherent GPU domains, the default substrate for frontier training and inference.
Full NVIDIA Blackwell record →Head to head
NVIDIA Blackwell vs AMD Instinct MI355X
NVIDIA Blackwell (NVIDIA) and AMD Instinct MI355X (AMD) both sit in Chips & Compute. NVIDIA Blackwell shipped more tracked changes in the last 30 days (5 vs 3). Every value below comes from the latest crawl of the vendors' own pages.
| Attribute | NVIDIA Blackwell NVIDIA | AMD Instinct MI355X AMD |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | GB200 NVL72 | MI355X |
| Entry cost | Pricing is not published (enterprise/quote-only) | Enterprise hardware, pricing not published |
| Pricing tiers | — | Open Source free |
| Model stack | Blackwell · Blackwell B200 · Grace CPU | CDNA · CDNA 4 · ROCm |
| Context window | — | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 5 | 3 |
| Origin | Global | Global |
| Capabilities | 72-GPU NVLink domain, FP4 inference, HBM3E 192GB, CUDA ecosystem, Second-generation Transformer Engine, Fifth-generation NVLink, FP4 AI Support, Tensor Cores with microscaling formats | 288GB HBM3E, FP4/FP6 support, ROCm 7, open rack designs, DPX compute partition mode, CPX compute partition mode, NPS2 memory partitioning, GPU virtualization support |
AMD Instinct MI355X
288GB HBM3E accelerators with the ROCm software stack, used by several inference providers.
Full AMD Instinct MI355X record →