NVIDIA GPU
-
NVIDIA H100 NVL
Hopper Architecture
Securely Accelerate Workloads From Enterprise to Exascale- 96GB HBM3 Memory
- MPC 350w-400ｗ
-
NVIDIA RTX 2000 Ada
Ada Lovelace Architecture
Design and Simulations- 16GB GDDR6 Memory
- MPC 70W
-
NVIDIA H100 Tensor Core GPU
Hopper Architecture
Securely Accelerate Workloads From Enterprise to Exascale- SXM 700W, PCIe 300-350W
- SXM 80GB HBM3, PCIe 80GB HBM2e Memory
-
NVIDIA A800 40GB Active
Ampere Architecture
HPC、AI、Data Science- 40GB HBM2 Memory
- MPC 240W
-
NVIDIA A10 Tensor Core GPU
Ampere Architecture
AI, 3D, VDI- 24GB GDDR6 Memory
- MPC 150W
-
NVIDIA A30 Tensor Core GPU
Ampere Architecture
Enterprise Server- 24GB HBM2 Memory
- MPC 165W
-
NVIDIA A100 Tensor Core GPU
Ampere Architecture
HPC and AI- 80GB HBM2e Memory
- SXM 400W, PCIe 300W
-
NVIDIA RTX 4500 Ada
Ada Lovelace Architecture
Design and Simulations- 24GB GDDR6 Memory
- MPC 210W
-
NVIDIA RTX 4000 Ada
Ada Lovelace Architecture
Design and Simulations- 20GB GDDR6 Memory
- MPC 130W
-
NVIDIA L40S
Ada Lovelace Architecture
AI and Graphics- 48GB GDDR6 Memory
- MPC 350W
-
NVIDIA RTX 5000 Ada
Ada Lovelace Architecture
Design and Simulations- 32GB GDDR6 Memory
- MPC 250W
-
NVIDIA RTX 6000 Ada
Ada Lovelace Architecture
high-End Design- 48GB GDDR6 Memory
- MPC 300W
-
NVIDIA RTX 4000 SFF Ada
Ada Lovelace Architecture
Professional Graphic Board- 20GB GDDR6 Memory
- MPC 70W
-
NVIDIA RTX A2000 12GB
Ampere Architecture
Compact Design- 12GB GDDR6 Memory
- MPC 70W
-
NVIDIA RTX A6000
Ampere Architecture
High-End Graphics Board- 48GB GDDR6 Memory
- MPC 300W