NVIDIA H100 NVL 94GB

Overview

The NVIDIA H100 NVL 94GB is a high-performance GPU accelerator designed to meet the demands of large-scale AI, machine learning, and high-performance computing (HPC) workloads. Built on the NVIDIA Hopper architecture, it delivers exceptional performance, scalability, and energy efficiency, making it ideal for modern data centers and enterprise AI applications.

Features

• Architecture: NVIDIA Hopper
• GPU Memory: 94GB HBM3
• Memory Bandwidth: 3.9 TB/s
• Thermal Design Power (TDP): 350–400W (configurable)
• Form Factor: Dual-slot PCIe Gen5
• Cooling: Passive heat sink (requires system airflow)
• Interconnect:
• NVIDIA NVLink: 600 GB/s
• PCIe Gen5: 128 GB/s
• Multi-Instance GPU (MIG): Supports up to 7 MIGs at 12GB each
• Decoders: 7 NVDEC, 7 JPEG
• Compatibility: Supports NVIDIA AI Enterprise software suite

Specifications

• CUDA Cores: 14,592
• Tensor Cores:
• FP64: 30 teraFLOPS
• FP64 Tensor Core: 60 teraFLOPS
• FP32: 60 teraFLOPS
• TF32 Tensor Core: 835 teraFLOPS (with sparsity)
• BFLOAT16 Tensor Core: 1,671 teraFLOPS (with sparsity)
• FP16 Tensor Core: 1,671 teraFLOPS (with sparsity)
• FP8 Tensor Core: 3,341 teraFLOPS (with sparsity)
• INT8 Tensor Core: 3,341 TOPS
• PCIe Gen5 Bandwidth: 128 GB/s
• NVLink Bandwidth: 600 GB/s
• Cooling: Passive heat sink (requires system airflow)
• Form Factor: Dual-slot PCIe Gen5
• Maximum TDP: 350–400W (configurable)
• Warranty: 1-year manufacturer warranty