H100 NVL GPU
The H100 NVL is optimized for large language model inference, featuring dual-GPU design with 94GB combined memory and high NVLink bandwidth.
Starting Price
$1.40/hr
Available on 2 cloud providers
Key Specifications
💾Memory
94GB VRAM
🏗️Architecture
Hopper
⚙️Compute Units
N/A
🧮Tensor Cores
456
Technical Specifications
Hardware Details
ManufacturerNVIDIA
ArchitectureHopper
CUDA Cores14592
Tensor Cores456
RT CoresN/A
Compute UnitsN/A
GenerationN/A
Memory & Performance
VRAM94GB
Memory InterfaceN/A
Memory Bandwidth3958 GB/s
FP32 Performance67 TFLOPS
FP16 Performance835 TFLOPS
INT8 PerformanceN/A
Performance
Computing Power
CUDA Cores14,592
Tensor Cores456
Computational Performance
FP32 (TFLOPS)67
FP16 (TFLOPS)835
Common Use Cases
LLM inference, generative AI, conversational AI
Machine Learning & AI
- Training large language models and transformers
- Computer vision and image processing
- Deep learning model development
- High-performance inference workloads
Graphics & Compute
- 3D rendering and visualization
- Scientific simulations
- Data center graphics virtualization
- High-performance computing (HPC)
Market Context
The H100 NVL sits within NVIDIA’s Hopper architecture lineup, positioned in the ultra performance tier. It’s designed specifically for data center and enterprise use.
Cloud Availability
Available across 2 cloud providers with prices ranging from $1.40/hr. Pricing and availability may vary by region and provider.
Market Position
Released in 2023, this GPU is positioned for enterprise and data center workloads.