The NVIDIA H100 NVL, built on the NVIDIA Hopper™ architecture, delivers industry-leading performance, scalability, and security for AI and high-performance computing (HPC) workloads. With innovations such as the Transformer Engine and fourth-generation Tensor Cores, it accelerates large language models (LLMs), securely handles enterprise workloads, and supercharges AI training with up to 4X performance improvement over previous models.
NVIDIA H100 NVL Tensor Core GPU
NVIDIA Hopper™
94GB HBM3
Up to 3,341 TFLOPS FP8 performance
LLM inference, AI training, large language models, high-performance computing (HPC), scientific computing
From $2.29/hr
Enhanced AI model training with FP8 precision.
Optimized for large language models like GPT-3.
Accelerates scientific and high-performance computing tasks.
Delivers up to 30X performance increase on large models like Megatron 530B.
Ideal for tasks like genome sequencing and 3D FFT.
