GPU clusters
Ubilink.AI Supercomputer
Compute
1K H100e
Chips
1,024
First operational
Nov 18, 2024
Ubilink.AI Supercomputer is a large GPU cluster operated by Ubilink AI, located in Taiwan, in the private sector. It came online around November 2024. At that moment it ranked number 104 among known clusters.
It is built on 1,024 NVIDIA H100 SXM5 80GB. That amounts to about 1K H100e of AI compute. The cluster draws roughly 1.78 MW. Its hardware is estimated at $39M.
Epoch AI rates the certainty of this record as confirmed.
Full record
- Owner
- Ubilink AI
- Users
- Cloud
- Sector
- Private
- Status
- Existing
- Country
- Taiwan
- Location
- Tucheng, New Taipei, Taiwan
- Primary chip
- NVIDIA H100 SXM5 80GB
- Primary chip count
- 1,024
- Total AI chips
- 1,024
- H100 equivalents
- 1K
- 8-bit throughput
- 2×10¹⁸ OP/s
- Power capacity
- 1.78 MW
- Hardware cost
- $39M
- First operational
- Nov 18, 2024
- Rank when it came online
- 104
- 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