NVIDIA A10
Universal mainstream data center GPU based on Ampere — 24 GB GDDR6, 150W, single-slot. Accelerates graphics, AI inference, virtual workstations, and video in the broadest range of enterprise servers.
Showing all 11 results
-
-
NVIDIA A16
Quad-GPU Ampere board purpose-built for high-density, graphics-rich VDI — 64 GB GDDR6 ECC, four GPUs per card, and up to 2x the user density for enterprise virtual desktops.
-
NVIDIA A2
Low-profile, low-power edge inference GPU with 16 GB GDDR6 ECC in a 40–60W envelope. Brings NVIDIA AI to space- and power-constrained edge and enterprise servers.
-
NVIDIA L40
Ada Lovelace universal data center GPU with 48 GB GDDR6 ECC and 18,176 CUDA cores. Purpose-built for VDI, Omniverse digital twins, rendering, and mixed graphics + AI workloads.
-
NVIDIA L40S
The universal Ada Lovelace GPU for the modern data center — 48 GB GDDR6 ECC, 18,176 CUDA cores, and 350W TDP delivering breakthrough performance for LLM inference, training, graphics, and video.
-
NVIDIA RTX 2000 Ada Generation
Entry-level Ada Lovelace professional GPU — 2,816 CUDA cores, 16GB GDDR6 ECC at 70W. Affordable professional graphics with AI and ray tracing for every desktop.
-
NVIDIA RTX 4000 Ada Generation
Compact single-slot professional GPU — 6,144 CUDA cores, 20GB GDDR6 ECC, 26.7 TFLOPS FP32 at just 130W for mainstream professional workstations.
-
NVIDIA RTX 4000 SFF Ada Generation
Small form factor professional GPU — 6,144 CUDA cores, 20GB GDDR6 ECC at just 70W with no external power. The most powerful low-profile professional card.
-
NVIDIA RTX 4500 Ada Generation
Mid-range Ada Lovelace professional GPU — 7,680 CUDA cores, 24GB GDDR6 ECC, 39.9 TFLOPS FP32 for reliable CAD, visualization, and AI-assisted design.
-
NVIDIA RTX 5000 Ada Generation
High-performance Ada Lovelace professional GPU — 12,800 CUDA cores, 32GB GDDR6 ECC, 65.3 TFLOPS FP32 for professional design, rendering, and AI workloads.
-
NVIDIA RTX 6000 Ada Generation
Flagship Ada Lovelace professional GPU — 18,176 CUDA cores, 48GB GDDR6 ECC, 91.1 TFLOPS FP32 for demanding CAD, rendering, simulation, and AI workflows.