GPU clusters
Texas A&M Grace
Compute
63.06 H100e
Chips
200
First operational
Nov 1, 2021
Texas A&M Grace is a large GPU cluster operated by Texas A&M, located in the United States, in the public sector. It came online around November 2021. At that moment it ranked number 108 among known clusters.
It is built on 200 NVIDIA A100. That amounts to about 63.06 H100e of AI compute. The cluster draws roughly 0.17 MW. Its hardware is estimated at $7M.
Epoch AI rates the certainty of this record as confirmed.
Full record
- Owner
- Texas A&M
- Users
- Academia
- Sector
- Public
- Status
- Existing
- Country
- United States
- Location
- College Station, Texas
- Primary chip
- NVIDIA A100
- Primary chip count
- 200
- Total AI chips
- 200
- H100 equivalents
- 63.06
- 8-bit throughput
- 1.2×10¹⁷ OP/s
- Power capacity
- 0.17 MW
- Hardware cost
- $7M
- First operational
- Nov 1, 2021
- Rank when it came online
- 108
- Certainty
- Confirmed
SourceEpoch AI, 'GPU Clusters'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/gpu-clusters. Licensed under CC BY 4.0.
← All gpu clusters