Nvidia H20

Nvidia H20

Export-compliant Hopper inference GPU with lower compute than H100.

Jump to: At a glance Specs FAQ Alternatives
Compare vs other GPUs →

At a glance

Hardware

Architecture
Hopper
Memory per GPU
96 GB HBM3
Memory bandwidth
4,000 GB/s
Release date
Q1 2024

Market

We don't currently track any H20 offers. See alternative GPUs.

Technical Specifications

Nvidia H20 · Per GPU

Compute
Precision support FP8FP16BF16TF32FP32FP64INT8
Memory
Capacity 96 GB HBM3
Bandwidth 4,000 GB/s
ECC Yes
Silicon
Architecture Hopper
Fabric and host
Host interface PCIe 5.0 x16
Power
Board power 400 W
Platform
Partitioning MIG, up to 7 instances
Salad Logo Salad
Our sponsor
Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour
Run RTX 50-series and 40-series cards without datacenter pricing
Pick a priority level to balance cost against interruptions
Per-second billing, with no charge for cold starts or image pulls
See SaladCloud pricing

Frequently Asked Questions

Why choose the H20?

96GB HBM3 at lower cost than H100. Large memory capacity suits inference for 70B models. Available in China where H100/H200 are restricted.

When is the H20 not a good fit?

Significantly reduced compute compared to H100. PCIe-only with no NVLink support. Better suited for memory-bound inference than training or latency-sensitive workloads.

Alternatives to Nvidia H20

Browse all GPUs

Last updated

Back to top ↑