Tesla 10k H100 Cluster

Compute

10K H100e

Chips

10,000

First operational

Aug 28, 2023

Tesla 10k H100 Cluster is a large GPU cluster operated by Tesla, located in the United States, in the private sector. It came online around August 2023. At that moment it ranked number 1 among known clusters.

It is built on 10,000 NVIDIA H100 SXM5 80GB. That amounts to about 10K H100e of AI compute. The cluster draws roughly 14.52 MW. Its hardware is estimated at $360M.

Epoch AI rates the certainty of this record as confirmed. There are claims of the cluster costing $300 million, however, that was not an official anouncement and might just be a BOTEC "30k per H100 times 10,000

Full record

Owner: Tesla
Users: Tesla
Sector: Private
Status: Existing
Country: United States
Location: "on prem" for Tesla
Primary chip: NVIDIA H100 SXM5 80GB
Primary chip count: 10,000
Total AI chips: 10,000
H100 equivalents: 10K
8-bit throughput: 2×10¹⁹ OP/s
Power capacity: 14.52 MW
Hardware cost: $360M
First operational: Aug 28, 2023
Rank when it came online: 1
Certainty: Confirmed