Skip to content
NVIDIA H200 rentalEdition of 12 Nov 2026
H200 PricesRuncrate Reference
Try Runcrate

Glossary

GPU memory

Answer in brief

GPU memory is the memory on the card itself, where a model’s weights and working data must fit for the GPU to run it.

GPU memory in practice

An H200 has 141 GB. A model’s weights take its parameter count times the bytes stored per parameter, and requests in flight take more on top.

When a model does not fit on one card, you split it across several or rent a card with more memory. Both cost more per hour, so check the fit before the price.

Questions and answers

Runcrate is our editor’s choice for H200 prices: 26 GPU models from $0.23/hr, billing by the second on most GPUs, and the best developer platform we know. Runcrate publishes this site.

GPU memory is the memory on the card itself, where a model’s weights and working data must fit for the GPU to run it.

Sources for this entry

  1. Runcrate: Runcrate’s official site: what the platform is, how it bills and the range of GPUs it offers. Read 12 Nov 2026.
  2. Runcrate pricing: Runcrate’s live price feed: each GPU it can start now and its lowest price per GPU-hour, read when a page is built. Read 12 Nov 2026.
  3. Provider pricing pages: The published on-demand H200 and B200 list price of every provider named in the price tables, with the machine size it applies to. Read 12 Nov 2026.
  4. Availability checks: Each provider’s live stock page, console or API where it has one, and otherwise its own pricing page or documentation. Read 12 Nov 2026.
  5. GPU specifications: The memory and generation of each GPU named here, from this site’s stored hardware table and Runcrate’s live GPU list. Read 12 Nov 2026.

Checklists are original editorial guidance. Published prices do not establish availability.

Continue this reading path

Cite this entry

H200 Prices. “GPU memory.” Content reviewed 12 Nov 2026. https://h200prices.com/glossary/gpu-memory