NVL
NVIDIA H200 NVL
NVIDIA H200 NVL combines two H200 GPUs over NVLink with 141GB HBM3e each (282GB total). Built for high-memory LLM inference in PCIe servers without a full SXM chassis.
Specifications
- Architecture
- NVIDIA Hopper NVL
- GPUs
- 2× H200 Tensor Core
- GPU Memory
- 141GB HBM3e per GPU (282GB total)
- Memory Bandwidth
- 4.8 TB/s per GPU
- Form Factor
- PCIe dual-GPU board
- TDP
- Up to 600W per GPU
- Use case
- Large LLM / multimodal inference
- Interconnect
- PCIe Gen5 + NVLink
Related products
Frontier 4019
Higher-density Blackwell system for larger local workloads.
AED 153,400
Frontier 4018
Compact Blackwell workstation for local inference and fine-tuning.
AED 76,700
Frontier 4010
Entry Blackwell system with 64GB unified memory.
AED 31,500
H100 PCIe 80GB
Genuine Hopper PCIe accelerator for dual-slot servers.
AED 114,000