AI hardware
Baidu Kunlun R200 (150W)
FP16 throughput
1.3×10¹⁴ FLOP/s
Memory
14.9 GB
TDP
150 W
Baidu Kunlun R200 (150W) is an AI accelerator designed by Kunlunxin Baidu (XPU-R), released in January 2022. It is built on a 7 nm process.
It carries 14.9 GB of memory at 477 GB/s of bandwidth. Its thermal design power is 150 W.
Full record
- Manufacturer
- Kunlunxin Baidu
- Type
- XPU-R
- Release date
- Jan 1, 2022
- FP32
- 3.2×10¹³ FLOP/s
- INT8
- 2.6×10¹⁴ OP/s
- Memory
- 14.9 GB
- Memory bandwidth
- 477 GB
- TDP
- 150 W
- Process node
- 7 nm
More from Kunlunxin Baidu
SourceEpoch AI, 'Machine Learning Hardware'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/machine-learning-hardware. Licensed under CC BY 4.0.
← All ai hardware