Lawrence Livermore NL El Capitan Phase 2

Compute

44.1K H100e

Chips

44,544

First operational

Nov 18, 2024

Lawrence Livermore NL El Capitan Phase 2 is a large GPU cluster operated by US Department of Energy, located in the United States, in the public sector. It came online around November 2024. At that moment it ranked number 5 among known clusters.

It is built on 44,544 AMD Instinct MI300A. That amounts to about 44.1K H100e of AI compute. The cluster draws roughly 35 MW. Its hardware is estimated at $607M.

Epoch AI rates the certainty of this record as confirmed.

Full record

Owner: US Department of Energy
Users: US Government, Lawrence Livermore NL, Scientific Research
Sector: Public
Status: Existing
Country: United States
Location: Lawrence Livermore National Laboratory 7000 East Ave, Livermore, CA 94550
Primary chip: AMD Instinct MI300A
Primary chip count: 44,544
Total AI chips: 44,544
H100 equivalents: 44.1K
8-bit throughput: 8.7×10¹⁹ OP/s
Power capacity: 35 MW
Hardware cost: $607M
First operational: Nov 18, 2024
Rank when it came online: 5
Certainty: Confirmed