Layer 2 · head to head
NVIDIA Vera Rubin VR200 NVL144 vs AMD Helios (Instinct MI455X)
The 2026 rack-scale fight. Both bet everything on HBM4, and HBM4 is sold out through the year.
| NVIDIA Vera Rubin VR200 NVL144 | AMD Helios (Instinct MI455X) | |
|---|---|---|
| Can you get it | Rentable by the hour from multiple clouds; purchasable at scale. | Rentable by the hour from multiple clouds; purchasable at scale. |
| Memory | HBM4. NVIDIA quotes 20.7 TB per rack at NVL72 scale; the NVL144 CPX configuration is quoted at 100 TB of fast memory per rack. | 31 TB of HBM4 per rack across 72 MI455X GPUs; 432 GB of HBM4 per GPU. |
| Bandwidth | Around 20 TB/s per package on initial shipments, against an original 22 TB/s target the memory suppliers missed. 1.6-1.7 PB/s aggregate per rack. | 260 TB/s scale-up per rack; 19.6 TB/s per GPU. |
| Compute | 8 exaFLOPS of FP4-class AI per NVL144 CPX rack, on NVIDIA's own figure. | 2.9 exaFLOPS FP4 and 1.4 exaFLOPS FP8 per rack, on AMD's own figures. |
| Power | Not published in comparable per-rack terms at time of writing. | Not published per rack. |
| Interconnect | NVLink, Rubin generation | Scale-up fabric, Helios rack architecture |
| Software | CUDA | ROCm |
| Workload | both | both |
NVIDIA Vera Rubin VR200 NVL144
For: Buyers who already committed to NVLink rack-scale and are taking the next generation. In practice that is a short list of hyperscalers and the largest neoclouds.
The catch: Effectively allocated rather than sold. First shipments began July 2026 and roughly 5,000-7,000 racks are expected across H2 2026 — a number worth weighing against the $725B of hyperscaler capex chasing them. The binding input is HBM4, which all three suppliers describe as committed or sold out through 2026, and NVIDIA already cut its bandwidth target because they could not hit it. A specification that moves before volume shipping is a supply story, not an engineering one.
Economics: The comparison that matters is against GB300, not against AMD: whether the throughput gain justifies waiting for an allocation you may not receive. For anyone outside the allocation list, the honest answer is that this part is not yet a purchasing option.
AMD Helios (Instinct MI455X)
For: Buyers with a working ROCm story who want more memory per GPU than NVIDIA sells, and a second source at rack scale.
The catch: ROCm is still the decision, not the silicon. The memory advantage per GPU is real and large — 432 GB against Blackwell-class parts — but it only pays if your stack runs on ROCm without a rewrite, and for most teams today it does not. Racks are quoted around $5-5.5M, which is one of very few public rack prices anywhere at this layer.
Economics: AMD's leverage here is memory capacity and being a second source, not price per FLOP. The commercial proof is commitment rather than benchmark: Oracle Cloud is the first hyperscaler offering a public MI450-series supercluster at 50,000 GPUs from Q3 2026, and OpenAI has committed to 6 GW of AMD Instinct with the first gigawatt in H2 2026.
Before either — can you power it?
Not published in comparable per-rack terms at time of writing. against Not published per rack.. In 2026 that comparison usually matters more than the FLOPS one: the US interconnection queue exceeds 2,600 GW with waits approaching five years, and roughly 80% of projects withdraw before energising.