NVIDIA · Ampere · 2020
A40 GPU accelerator (PCIe card)
A40 GPU accelerator (PCIe card): 48 GB GDDR6, 300 W, 10,752 CUDA cores. Launched October 5, 2020.
- Memory
- 48 GB
- Power
- 300 W
- Bus width
- 384 bit
Memory48 GB
7 of 32 in Data Center
Power300 W
12 of 40 by higher draw in Data Center
CUDA cores10,752
9 of 47 in Data Center
Current market
Affiliate links — we may earn a commission.
Specifications
Memory
- Capacity
- 48 GB
- Memory type
- GDDR6
- Bus width
- 384 bit
- Bandwidth
- 695.8 GB/s
Compute
- CUDA cores
- 10,752
- SM count
- 84
- TMUs
- 336
- ROPs
- 112
- FP32
- 37,420 GFLOPS
- FP64
- 1,168 GFLOPS
Clocks
- Base clock
- 1,305 MHz
- Boost clock
- 1,740 MHz
Board
- TDP
- 300 W
- Form factor
- datacenter
Physical
- Architecture
- Ampere
- Series
- Data Center
- Launch date
- October 5, 2020
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 A40 GPU accelerator (PCIe card) ranks 8th of 36 for FP32 throughput and 7th of 32 for memory capacity. Its 300 W TDP is above the 75 W PCIe slot-power ceiling.
Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16