NVIDIA® RTX Technology
Next Revolution of Visual Computing


NVIDIA Ada Lovelace
The NVIDIA Ada Lovelace architecture has been designed to provide revolutionary performance for ray
tracing and AI-based neural graphics. It delivers a dramatically higher baseline of GPU performance and
marks the tipping point for ray tracing and neural graphics.
NVIDIA RTX™ 6000 Ada Generation
NVIDIA RTX™ 6000 Ada Generation is the most powerful workstation GPU offering high-performance,
real-time ray tracing, AI-accelerated compute, and professional graphics rendering. Building upon the
major SM enhancements from the Ada Lovelace GPU, the NVIDIA Ada Lovelace architecture provides
more cores, higher clocks, and a larger L2 cache for more performance to enhance ray tracing
operations, tensor matrix operations, and frame rates with DLSS 3.0
NVIDIA RTX™ 4000 SFF Ada Generation
NVIDIA RTX™ 4000 SFF Ada Generation is the most powerful dual slot, low-profile workstation GPU offering high-performance, real-time ray tracing, AI-accelerated compute, and professional graphics rendering, all of this in a compact design with unmatched performance. Building upon the major SM enhancements from the Ada Lovelace GPU, the NVIDIA Ada Lovelace architecture provides more cores, higher clocks, and a larger L2 cache for more performance to enhance ray tracing operations, tensor matrix operations, and frame rates with DLSS 3.0.
Highlights | RTX 6000 Ada | RTX 4000 SFF Ada |
---|---|---|
Maximum Power Consumption | 300 W | 70 W |
Display Connectors | 4xDP 1.4 | 4xDP 1.4 |
System Interface | PCIe 4.0x1.6 | PCIe 4.0x1.6 |
Memory Bandwidth | 960 GB/sec | 280 GB/sec |
Memory Interface | 384-bit | 160-bit |
GPU Memory | 48GB GDDR6 | 20GB GDDR6 |
CUDA Cores | 18176 | 6144 |
Tensor Performance | 1457.0 TFLOPS | 306.8 TFLOPS |
RT Core Performance | 210.6 TFLOPS | 44.3 TFLOPS |
RT Cores | 142 | 48 |
Single Precision Performance | 91.1 TFLOPS | 19.2 TFLOPS |
Tensor Cores | 568 | 192 |
NVIDIA® Ampere Architecture-Based CUDA Cores
The NVIDIA® Ampere architecture’s CUDA® cores bring double-speed processing for single-precision floating point (FP32) operations and are up to 2X more power efficient than Turing GPUs. This provides significant performance gains for graphics workflows like 3D model development and compute workflows like desktop simulation for computer-aided engineering (CAE).
Highlights | A2000 | A4000 | A4500 |
---|---|---|---|
Tensor Cores | 104 | 192 | 224 |
Single Precision Performance | 8.0 TFLOPS | 19.2 TFLOPS | 23.7 TFLOPS |
RT Cores | 26 | 48 | 56 |
RT Core Performance | 15.6 TFLOPS | 37.4 TFLOPS | 46.2 TFLOPS |
Tensor Performance | 63.9 TFLOPS | 153.4 TFLOPS | 189.2 TFLOPS |
CUDA Cores | 3328 | 6144 | 7168 |
GPU Memory | 12GB GDDR6 with ECC | 16GB GDDR6 with ECC | 20GB GDDR6 with ECC |
Memory Interface | 192-bit | 256-bit | 320-bit |
Memory Bandwidth | 288 GB/sec | 488 GB/sec | 640 GB/sec |
System Interface | PCIe 4.0x16 | PCIe 4.0x16 | PCIe 4.0x16 |
Display Connectors | 4x mDP 1.4a | 4x mDP 1.4A | 4x mDP 1.4 |
Maximum Power Consumption | 70 Watts | 140 Watts | 200 Watts |
Highlights | A5500 | A5000 | A6000 |
---|---|---|---|
Maximum Power Consumption | 230 Watts | 230 Watts | 300 Watts |
Display Connectors | 4x Display Port 1.4a | 4x mDP 1.4a | 4x mDP 1.4a |
System Interface | PCIe 4.0 x16 | PCIe 4.0 x16 | PCIe 4.0 x16 |
Memory Bandwidth | 768GB/sec | 768GB/sec | 768GB/sec |
Memory Interface | 384-bit | 384-bit | 384-bit |
GPU Memory | 24GB GDDR6 with ECC | 24GB GDDR6 with ECC | 48GB GDDR6 with ECC |
CUDA Cores | 10240 | 8192 | 10752 |
Tensor Performance | 272.8 TFLOPS | 222.2 TFLOPS | 309.7 TFLOPS |
RT Core Performance | 66.6 TFLOPS | 54.2 TFLOPS | 75.6 TFLOPS |
RT Cores | 80 | 64 | 84 |
Single Precision Performance | 34.1 TFLOPS | 27.8 TFLOPS | 38.7 TFLOPS |
Tensor Cores | 320 | 256 | 336 |

Target Industries: Architecture, Engineering & Construction
The architecture, engineering, and construction (AEC) industry is undergoing a transformation. Projects are becoming more complex and team members are increasingly working remotely, complicating workflows, communication, and collaboration. Reimagine the cities of the future powered by NVIDIA® RTX professional visual computing solutions based on NVIDIA® Ampere architecture that deliver the high levels of performance needed to meet today’s most demanding workflows. Offer AEC customers the ability to take advantage of the latest advancements in NVIDIA® Omniverse, real-time ray tracing, virtual reality (VR), 3D graphics virtualization, and AI-augmented tools to optimize design workflows.
Target Industries: Manufacturing & Product Design
Traditional product development processes have evolved rapidly. Product design teams are embracing virtual reality, physically based rendering, graphics virtualization, real-time simulation, and AI. These new GPU-accelerated technologies are helping manufacturers radically improve how teams design and collaborate to deliver better products faster than ever. Designers have typically faced costly trade-offs to get products to market on time. Optimizing a design for performance often meant sacrificing cost of a part, as well as additional operating costs associated with an engineer’s time refining designs. Help customers understand that embracing NVIDIA® RTX professional visual computing solutions, powered by the NVIDIA® Ampere Architecture, means trade-offs can be optimized to deliver the best possible results. Designers and engineers in every can now improve all facets of their design experience without making sacrifices.
Target Industries: Media & Entertainment
Advancements in pivotal technologies virtual production, rendering, simulation, and artificial intelligence continue to propel the future of media and entertainment, reinventing how content is created, delivered, and consumed. Lead customers into the future of storytelling with the latest NVIDIA® technologies that are engineered to power the most advanced, visually rich feature films and television shows ever created.
