Buying in volume? Request a bulk quote
We source this item through our supplier network and do not hold inventory. Price and availability are confirmed with you before any order is accepted.
Questions about this part? Talk to us.
Phone +1 872 293 4196 · Email supply@allchipsupply.com
Location: USA · Shipping: Worldwide Shipping
The NVIDIA H200 NVL is a Hopper-architecture data center GPU in a passively cooled, dual-slot PCIe card. It carries 141 GB of HBM3e memory with 4.8 TB/s of bandwidth, the same memory configuration as the H200 SXM module, which makes it a strong fit for large language model inference in standard PCIe servers.
It connects over PCIe 5.0 x16, and cards can be linked with 2-way or 4-way NVLink bridges at 900 GB/s. Maximum power is configurable up to 600 W, and Multi-Instance GPU (MIG) can split one card into up to seven instances of 18 GB each. This listing is the GPU only, without a power adapter or NVLink bridge. Install it in a server that is certified for the H200 NVL.
| Architecture | NVIDIA Hopper |
|---|---|
| GPU memory | 141 GB HBM3e |
| Memory bandwidth | 4.8 TB/s |
| Interface | PCIe 5.0 x16 |
| Interconnect | 2- or 4-way NVLink bridge, 900 GB/s |
| Max TDP | Up to 600 W (configurable) |
| MIG | Up to 7 instances @ 18 GB |
| Cooling | Passive |
Specifications are summarized from manufacturer and listing information; confirm against the manufacturer datasheet before purchase.
Manufacturer datasheet / product page (opens the manufacturer's website)
NVIDIA Hopper · 80 GB HBM2e · 2.0 TB/s
NVIDIA Blackwell · 180 GB HBM3e · 7.7 TB/s
200 Gb/s · PCIe 5.0 x16 · 1
NVIDIA Ampere · 80 GB HBM2e, ECC · ~1.9 TB/s
