AI Models & Assistants / Knowledge library
H100 SXM 80GB
NVIDIA accelerator; 80GB device memory.
Why learn H100 SXM 80GB?
High throughput for supported workloads; SXM requires a compatible server platform.
The problem it solves
Provides compute and memory for supported workloads using CUDA · vLLM · TensorRT-LLM.
Where it came from
H100 SXM 80GB: NVIDIA accelerator; 80GB device memory. H denotes Hopper; SXM is a server module, not a desktop PCIe card. High throughput for supported workloads; SXM requires a compatible server platform.
Build your understanding
Work through these exercises in order. Try the task before opening a reference.
- Explain what H100 SXM 80GB does.
- Identify a use case for H100 SXM 80GB.
- Describe a limitation of H100 SXM 80GB.
- Name a compatible tool for H100 SXM 80GB.
- Compare H100 SXM 80GB against an alternative.
Documentation and sources
- Primary source / model card (www.nvidia.com)
Catalog research notes
- See the AI Workbench for source dates, pricing evidence and configuration details.