NVIDIA · Ampere · 2021
A30 GPU accelerator (PCIe card)
A30 GPU accelerator (PCIe card): 24 GB HBM2, 165 W, 3,584 CUDA cores. Launched April 12, 2021.
- Memory
- 24 GB
- Power
- 165 W
- Bus width
- 3,072 bit
Memory24 GB
9 of 32 in Data Center
Power165 W
36 of 40 by higher draw in Data Center
CUDA cores3,584
16 of 47 in Data Center
Current market
Affiliate links — we may earn a commission.
Specifications
Memory
- Capacity
- 24 GB
- Memory type
- HBM2
- Bus width
- 3,072 bit
- Bandwidth
- 933.1 GB/s
Compute
- CUDA cores
- 3,584
- SM count
- 56
- TMUs
- 224
- ROPs
- 96
- FP32
- 10,320 GFLOPS
- FP64
- 5,161 GFLOPS
Clocks
- Base clock
- 930 MHz
- Boost clock
- 1,440 MHz
Board
- TDP
- 165 W
- Form factor
- datacenter
Physical
- Architecture
- Ampere
- Series
- Data Center
- Launch date
- April 12, 2021
Not recorded by the source: generation, codename, process and transistors, or 7 further fields.
Die figure
Silicon, made visible
Die area is drawn against the largest recorded die in the catalog. Shader dots use a labeled, card-specific ratio so both early and modern GPUs remain legible.
Catalog context
Within its series, the A30 GPU accelerator (PCIe card) ranks 15th of 36 for FP32 throughput and 9th of 32 for memory capacity. Its 165 W TDP is above the 75 W PCIe slot-power ceiling.
Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16