NVIDIA
AI AcceleratorsNVIDIA H100 SXM 80GB
The reference training accelerator for multi-GPU nodes, deployed eight to a baseboard with full NVLink bandwidth between every GPU.
- Architecture
- Hopper
- GPU memory
- 80GB HBM3
- Memory bandwidth
- 3.35TB/s
AI Accelerators
NVIDIA
NVIDIA H200 SXM 141GB
Model H200
Hopper-generation accelerator with the largest memory pool in its family, suited to serving and fine-tuning large language models that outgrow 80GB parts.
Quantity
No prices online. Add what you need and we reply with an all-in price and a delivery date.
// NVIDIA H200 SXM 141GB specifications
| Architecture | Hopper |
|---|---|
| GPU memory | 141GB HBM3e |
| Memory bandwidth | 4.8TB/s |
| Interconnect | NVLink, 900GB/s |
| Form factor | SXM module on HGX baseboard |
| Max power | Up to 700W |
Specifications are indicative and confirmed on quote. Product and brand names belong to their respective owners and are used for identification only.
Before you order: AI Accelerators
The questions we ask before quoting. Answer them in the line notes and the first reply is usually the final one.
- Module parts (SXM, OAM) only fit a matching baseboard and chassis. Tell us the host platform, or quote the server alongside them.
- Passive PCIe cards rely on server airflow. Check the chassis is rated for the power of the card before ordering.
- For multi-GPU work, say whether you need NVLink bridges or a switched fabric. It changes what gets quoted.
- Memory size usually decides the model: size it against the largest model and batch you plan to run.
More in AI Accelerators
All AI Accelerators
NVIDIA
AI AcceleratorsNVIDIA H100 NVL 94GB
A PCIe card version of Hopper with extra memory, built for LLM inference in standard air-cooled servers and bridged in pairs over NVLink.
- Architecture
- Hopper
- GPU memory
- 94GB HBM3
- Memory bandwidth
- 3.9TB/s
NVIDIA
AI AcceleratorsNVIDIA L40S 48GB
A general-purpose data-centre GPU that covers inference, fine-tuning, rendering and virtual workstations from one PCIe card.
- Architecture
- Ada Lovelace
- GPU memory
- 48GB GDDR6 with ECC
- Memory bandwidth
- 864GB/s