NVIDIA · Ampere (derived from codename prefix) · 2021
RTX A2000 — 12 GB
RTX A2000 — 12 GB: 12 GB GDDR6, 70 W, 3,328 CUDA cores. Launched August 10, 2021 at $449.
- Memory
- 12 GB
- Power
- 70 W
- Bus width
- 192 bit
Memory12 GB
23 of 40 in RTX
Power70 W
25 of 38 by higher draw in RTX
CUDA cores3,328
27 of 38 in RTX
Launch price$449
18 of 22 in RTX
Current market
Affiliate links — we may earn a commission.
Specifications
Memory
- Capacity
- 12 GB
- Memory type
- GDDR6
- Bus width
- 192 bit
- Memory clock
- 1,500 MHz
- Bandwidth
- 288 GB/s
Compute
- CUDA cores
- 3,328
- SM count
- 26
- TMUs
- 104
- ROPs
- 48
- FP32
- 7,987 GFLOPS
- FP64
- 124.8 GFLOPS
- Pixel fill rate
- 57.6 GP/s
- Texture fill rate
- 124.8 GT/s
Clocks
- Base clock
- 562 MHz
- Boost clock
- 1,200 MHz
Board
- TDP
- 70 W
- Bus interface
- PCIe 4.0 x16
- Form factor
- mobile
- Launch MSRP
- 449 USD
Physical
- Architecture
- Ampere (derived from codename prefix)
- Codename
- GA106-850-A1
- Process
- 8 nm
- Series
- RTX
- Launch date
- August 10, 2021
Not recorded by the source: generation, transistors, die size and external power required.
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 RTX A2000 ranks 39th of 45 for FP32 throughput and 23rd of 40 for memory capacity. Its 70 W TDP is within the 75 W PCIe slot-power ceiling.
Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16