NVIDIA logo

Reserve your NVIDIA H100 Tensor Core GPU today with Civo

Be the first to add one of the most powerful NVIDIA GPUs into your infrastructure.

NVIDIA H100 Tensor Core GPU

Pioneering AI training and inference with NVIDIA H100 Tensor Core GPU

  • Optimized for AI

    With fourth-generation Tensor Cores and the Transformer Engine, the H100 excels in AI model training, especially for large language models like GPT-3.

  • Unmatched Memory Technology

    Featuring 4 GB or 80 GB HBM2e memory and incredible bandwidth, it's set to handle the most memory-intensive AI tasks.

  • Scalability and Security

    Designed for scalable multi-GPU systems, it ensures both high performance and robust security for data center operations.

Reserve your GPU today

Take an in-depth look

NVIDIA H100 SXM specifications
NVIDIA H100 SXM specifications NVIDIA logo
FP64 34 teraFLOPS
FP64 Tensor Core 67 teraFLOPS
FP32 67 teraFLOPS
TF32 Tensor Core 989 teraFLOPS
BFLOAT16 Tensor Core 1,979 teraFLOPS
FP16 Tensor Core 1,979 teraFLOPS
FP8 Tensor Core 3,958 teraFLOPS
INT8 Tensor Core 3,958 TOPS
GPU Memory 80GB
GPU memory bandwidth 3.35TB/s
Decoders 7 NVDEC
7 JPEG
Interconnect NVLink: 900GB/s PCIe Gen5: 128GB/s
Ideal for Large-scale AI Training, Conversational AI
Download the Data Sheet

Frequently Asked Questions

How can I reserve the NVIDIA H100 Tensor Core GPU?

To reserve the NVIDIA H100 Tensor Core GPU, you need to schedule a meeting with our team. During this meeting, we will discuss the next steps and answer any queries you might have.

Can I get a demo of the NVIDIA H100 Tensor Core GPU before purchasing?

If you're interested in a demo of the NVIDIA H100 Tensor Core before purchasing, it's possible to arrange one. You can set up a meeting with someone from the Civo team who will demonstrate how the chip works, specifically in conjunction with Civo.