NVIDIA H100 NVL NVH100NVLTCGPU-KIT Tensor Core GPU

Price:
$29,218.00
PNYSKU: SAI-9812079
Model Number: NVH100NVLTCGPU-KIT
Condition: New
In stock:  No
Price:
Sale price$29,218.00

NOTE: Availability 1-3 Weeks. Lead times may vary.

Get a Quote
NVIDIA H100 NVL NVH100NVLTCGPU-KIT Tensor Core GPU

NVIDIA H100 NVL NVH100NVLTCGPU-KIT Tensor Core GPU

SPECIAL ORDER ITEM

This product is available for special order and may take longer to ship.

AVAILABILITY & SHIPPING

We’re happy to source this item specifically for you! While it may take a bit more time to arrive, we’ll keep you informed every step of the way. Shipping timelines can vary based on the manufacturer's fulfillment schedule.

NEED IT SOONER?

Contact us to explore expedited options or find a comparable in-stock alternative.

SPECIAL ORDER FULFILLMENT

Saitech Inc. partners with top-tier manufacturers and authorized distributors to fulfill special order requests — including hard-to-find, end-of-life, and build-to-order products. Our team ensures every special order is handled with precision, transparency, and dedicated support from start to finish.

  • Overview

The NVIDIA H100 NVL Tensor Core GPU is built for AI, deep learning, and high-performance computing at scale. Designed for data centers and enterprise environments, it delivers up to 5X faster performance on Llama 2 70B compared to NVIDIA A100 systems, with improved power efficiency and reduced latency.

With 1.5X higher throughput than the H100 PCIe, the H100 NVL offers top-tier performance across large AI models and intensive training tasks. It combines NVLink architecture, enhanced memory bandwidth, and high compute density, making it the most capable GPU in the H100 series for large-scale inference and training workflows.

  • FP64 -30 teraFLOPS
  • FP64 Tensor Core - 60 teraFLOPS
  • FP32 - 60 teraFLOPS
  • TF32 Tensor Core - 835 teraFLOPS
  • BFLOAT16 Tensor Core - 1,671 teraFLOPS
  • FP16 Tensor Core - 1,671 teraFLOPS
  • FP8 Tensor Core - 3,341 teraFLOPS
  • INT8 Tensor Core - 3,341 teraFLOPS
  • GPU Memory - 94GB
  • GPU Memory Bandwidth - 3.9TB/s
  • Decoders 7 NVDEC / 7 JPEG
  • Max Thermal Design Power (TDP)- 350-400W (configurable)
  • Form Factor - PCIe dual-slot air-cooled
  • Interconnect - NVIDIA NVLINK: 600GB/s
  • PCIe Gen5 - 128GB/s
  • Server Options Partner and NVIDIA
  • NVIDIA Enterprise Included

Designed to operate in power-constrained data centers, the H100 NVL balances performance with energy efficiency, ensuring that high-density AI workloads remain cost-effective. 


Product information, pricing, availability, images or discounts are subject to change without notice and may not always reflect the most current details. In the event of pricing or availability discrepancies, we reserve the right to cancel or adjust orders. Customers will be notified and may choose to proceed or cancel.

You may also like

Recently viewed