> ## 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.

# H100 (InfiniBand)

> Specifications, pricing, and availability for the H100 (InfiniBand) GPU instance

These instances are powered by eight NVIDIA H100 Hopper GPUs, each with 80 GB of HBM3 memory. As the industry-defining accelerator of the previous generation, the H100 remains a powerful and reliable workhorse for a wide range of large-scale AI workloads. GPUs are fully connected with NVLink, and Nodes are linked with a 400G NDR InfiniBand fabric, providing a robust architecture for distributed training and inference.

## Specifications

| Feature              | Detail                                                                                                                                                                                                                                                                                                                                                                                                                           |
| :------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Category**         | Mid-large Size Model Training & Inference                                                                                                                                                                                                                                                                                                                                                                                        |
| **Instance ID**      | `gd-8xh100ib-i128`                                                                                                                                                                                                                                                                                                                                                                                                               |
| **GPU**              | 8x NVIDIA H100                                                                                                                                                                                                                                                                                                                                                                                                                   |
| **GPU RAM**          | 80 GB                                                                                                                                                                                                                                                                                                                                                                                                                            |
| **GPU Connectivity** | InfiniBand & NVLink                                                                                                                                                                                                                                                                                                                                                                                                              |
| **CPU Model**        | Intel Sapphire Rapids 8462Y+ (2.80 GHz)                                                                                                                                                                                                                                                                                                                                                                                          |
| **vCPUs**            | 128                                                                                                                                                                                                                                                                                                                                                                                                                              |
| **RAM**              | 2048 GB                                                                                                                                                                                                                                                                                                                                                                                                                          |
| **Local Storage**    | 61.44 TB                                                                                                                                                                                                                                                                                                                                                                                                                         |
| **Network Speed**    | Dual-port 100GbE                                                                                                                                                                                                                                                                                                                                                                                                                 |
| **Availability**     | [**RNO2A**](/platform/regions/us-west#rno2a)<br />[**US-EAST-01A**](/platform/regions/us-east#us-east-01a)<br />[**US-EAST-04A**](/platform/regions/us-east#us-east-04a)<br />[**US-EAST-06A**](/platform/regions/us-east#us-east-06a)<br />[**US-WEST-01A**](/platform/regions/us-west#us-west-01a)<br />[**US-WEST-04A**](/platform/regions/us-west#us-west-04a)<br />[**US-WEST-09B**](/platform/regions/us-west#us-west-09b) |

## Primary use cases

Large-scale AI training, high-performance inference serving, and a wide variety of HPC simulations.

## Recommended models

Quantized versions of the latest open-source models such as DeepSeek V4 Flash, Qwen 3.5 397B-A17B, Kimi K2.6, MiniMax M2.7 and other large models requiring substantial GPU memory for a single Node through the use of tensor parallelism.