NVIDIA H200 SXM: specs, pricing and what it can run

Same Hopper compute as H100 with 76% more memory and 43% more bandwidth. For inference, which is memory-bound, that bandwidth is the whole story.

Specifications

SpecNVIDIA H200 SXM
ArchitectureHopper
Released2024
Memory141 GB HBM3e
Memory bandwidth4,800 GB/s
Dense FP16989 TFLOPS
FP8 tensor coresYes
Board power700 W
InterconnectNVLink 4.0 (900 GB/s)
Segmentdatacenter

What fits in 141 GB

Weights only, at 85% of nominal capacity to leave room for the KV cache and activations. Long-context serving needs materially more headroom than this table implies.

QuantisationLargest model (weights only)
FP16~64B parameters
FP8 / INT8~128B parameters
4-bit~257B parameters

Rental cost

Indicative on-demand pricing runs roughly $2.50–$6.00 per GPU-hour depending on provider, region, and commitment. Spot and reserved capacity sit well below that band. These are ranges rather than quotes: street prices move week to week, so check live cloud price feed before budgeting.

Related

Deploy a model with Swfte Connect

One gateway, every provider, per-token cost visibility. Swap models without touching your code.