The primary focus of this wiki. Covers GeForce consumer cards, Quadro/RTX Pro workstation cards, Tesla/compute GPUs, and NVIDIA's full product history from the NV1 through the current Blackwell generation.
GPU Wiki
NVIDIA GPU Wiki
NVIDIA GPU specifications, architectures, release history, driver notes, and GeForce, workstation, compute, and legacy records.
Popular Series
Architecture
Segment
Popular GPU entries
| GPU | Architecture | Launch Date | CUDA Cores | Memory | Bus Width | TDP/TBP | Segment |
|---|---|---|---|---|---|---|---|
| H200 NVL | Hopper | 2024-11-18 | 16,896 | 141 GB HBM3e | 6,144-bit | 600 W | Data Center |
| L20 | Ada Lovelace | 2023-11-16 | 11,776 | 48 GB GDDR6 | 384-bit | 275 W | Data Center |
| H100 CNX | Hopper | 2023-03-21 | 14,592 | 80 GB HBM2e | 5,120-bit | 350 W | Data Center |
| H100 NVL 94 GB | Hopper | 2023-03-21 | 16,896 | 94 GB HBM3 | 6,016-bit | 400 W | Data Center |
| H100 PCIe 96 GB | Hopper | 2023-03-21 | 16,896 | 96 GB HBM3 | 5,120-bit | 700 W | Data Center |
| L4 | Ada Lovelace | 2023-03-21 | 7,424 | 24 GB GDDR6 | 192-bit | 72 W | Data Center |
| L40 CNX | Ada Lovelace | 2022-10-13 | 18,176 | 24 GB GDDR6 | 384-bit | 300 W | Data Center |
| L40G | Ada Lovelace | 2022-10-13 | 18,176 | 24 GB GDDR6 | 384-bit | 300 W | Data Center |
| L40S | Ada Lovelace | 2022-10-13 | 18,176 | 48 GB GDDR6 | 384-bit | 300 W | Data Center |
| H100 PCIe 80 GB | Hopper | 2022-10-01 | 14,592 | 80 GB HBM2e | 5,120-bit | 350 W | Data Center |