LOTA read throughput
Company: CoreWeave
The claim, verbatim
LOTA (Local Object Transport Accelerator) serves cached reads at up to 7 GB/s per GPU
Source (primary)
CoreWeave AI Object Storage: Cross-region writes, Archive - CoreWeave (-, news_article)
View cached copy (2026-09-19)Live source ↗
Quote: “serving cached reads at up to 7 GB/s per GPU”
How we checked this
Checked on September 24, 2026. The cited source supports every part of this claim.
The blog expands the LOTA acronym and says it serves cached reads at up to 7 GB/s per GPU.
Confirmed in the source:
- LOTA stands for Local Object Transport Accelerator
- LOTA serves cached reads at up to 7 GB/s per GPU
What we did: Read our cached copy of the publisher (https://www.coreweave.com/blog/new-in-coreweave-ai-object-storage-cross-region-writes-and-archive-storage) in full (16,354 characters, retrieved September 19, 2026) and checked each assertion in the claim against it.
Additional evidence
confirms CoreWeave AI Object Storage: Cross-region writes, Archive - CoreWeave
Quote: “serving cached reads at up to 7 GB/s per GPU”