GPU Wiki Architecture
Ampere
Architecture notes pending source review.
- Launch era
- Pending source review.
- Source review
- Pending
Related GPUs
118 entries
| GPU | Architecture | Launch Date | CUDA Cores | Memory | Bus Width | TDP/TBP | Segment |
|---|---|---|---|---|---|---|---|
| GeForce RTX 3050 8 GB | Ampere | 2022-01-27 | 2,560 | 8 GB GDDR6 | 128-bit | 130 W | Desktop |
| GeForce RTX 3060 Ti GDDR6X | Ampere | 2022-10-19 | 4,864 | 8 GB GDDR6X | 256-bit | 225 W | Desktop |
| GeForce RTX 3070 TiM | Ampere | 2022-11-01 | 5,888 | 8 GB GDDR6 | 256-bit | 220 W | Desktop |
| GeForce RTX 3070 Ti 8 GB GA102 | Ampere | 2022-10-21 | 6,144 | 8 GB GDDR6X | 256-bit | 290 W | Desktop |
| GeForce RTX 3050 OEM | Ampere | 2022-01-04 | 2,304 | 8 GB GDDR6 | 128-bit | 130 W | Desktop |
| GeForce RTX 3060 Ti GA103 | Ampere | 2022-02-23 | 4,864 | 8 GB GDDR6 | 256-bit | 200 W | Desktop |
| GeForce RTX 3080 Ti 20 GB | Ampere | 2022-01-01 | 10,240 | 20 GB GDDR6X | 320-bit | 350 W | Desktop |
| Switch 2 GPU | Ampere | 2025-06-05 | 1,536 | 12 GB LPDDR5X | 128-bit | 40 W | Console |
| GeForce RTX 3060 12 GB | Ampere | 2021-02-25 | 3,584 | 12 GB GDDR6 | 192-bit | 170 W | Desktop |
| GeForce MX570 | Ampere | 2021-12-17 | 2,048 | 2 GB or 4 GB depending on OEM implementation GDDR6 | 64-bit | 15 to 45 W, OEM dependent | Desktop |
More architecture facts
- Architecture name
- Ampere
- Predecessor
- Not yet documented.
- Successor
- Not yet documented.
- Process nodes
- Not yet documented.
- Important chips
- Not yet documented.
- Memory technologies
- Not yet documented.
- CUDA / RT / Tensor generation
- Not yet documented.
- Consumer series
- DRIVE, GeForce MX Series, GeForce RTX 20 Series, GeForce RTX 30 Series, GeForce RTX 40 Series, GRID, Mining GPUs, Nintendo Switch GPU, NVIDIA A-Series, NVIDIA RTX A Series, Tegra
- Workstation / professional series
- Not yet documented.
- Data center series
- Not yet documented.