> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GB300 NVL72 Spectrum-X RoCE

> Specifications and availability for the GB300 NVL72 Spectrum-X RoCE GPU instance

Powered by two NVIDIA GB300 Grace Blackwell Ultra Superchips (four Blackwell Ultra GPUs, each with an unprecedented 279 GB of memory), these instances represent the absolute pinnacle of our high-performance computing offerings. These instances form part of a larger NVL72 rack architecture which boasts 20.1 TB of total GPU memory, interconnected by 5th-generation NVLink for a seamless, rack-scale memory fabric. For clustering, they are equipped with next-generation NVIDIA Spectrum-X RoCE (RDMA over Converged Ethernet), leveraging BlueField-3 and ConnectX-8 SuperNICs for large scale AI in Ethernet-based cloud environments.

## Specifications

| Feature                   | Detail                            |
| :------------------------ | :-------------------------------- |
| **Category**              | State-of-the-Art Compute          |
| **Instance ID**           | `gb300-4x-e`                      |
| **GPU**                   | 4x NVIDIA GB300                   |
| **GPU RAM**               | 279 GB                            |
| **GPU Connectivity**      | Spectrum-X RoCE & NVLink          |
| **CPU Model**             | 2x NVIDIA Grace Arm v9 (3.10 GHz) |
| **vCPUs**                 | 144                               |
| **RAM**                   | 960 GB                            |
| **Local Storage**         | 61.44 TB                          |
| **NIC Config**            | Dual-port 200GbE                  |
| **Default GPU driver**    | `595`                             |
| **Compatible GPU driver** | `580`, `595`                      |
| **Availability**          | Contact sales for availability    |

## Primary use cases

Training next-generation foundation models in the trillion-parameter class, massive-scale and high-fidelity inference on the most complex AI models, and scientific simulations requiring maximum memory capacity and the fastest data throughput.

## Recommended models

Next-generation frontier models (multi-trillion parameters), state-of-the-art multimodal systems, and large-scale scientific discovery models.