Access the most powerful visual computing capabilities in thin and light mobile workstations anytime, anywhere. NVIDIA RTX™ professional laptop GPUs fuse speed, portability, large memory capacity, enterprise-grade reliability, and the latest RTX technology—including real-time ray tracing, advanced graphics, and accelerated AI—to tackle the most demanding creative, design, and engineering tasks on the go.
This new generation of laptop GPUs, based on the NVIDIA Ada Lovelace architecture, provides massive breakthroughs in speed, performance and power efficiency so you can explore a new realm of possibility.
NVIDIA Ada Lovelace Architecture
Streaming Multiprocessors
Up to 2X performance and power efficiency
Third-Generation
RT Cores
Up to 2X ray tracing performance
Fourth-Generation
Tensor Cores
Up to 4X performance with DLSS 3 AI-based rendering
NVENC / NVDEC
Up to two video encode/decode engines with support for AV1.
Large Memory
Up to 16GB GDDR6 for complex projects and datasets.
MAX-Q technology* introduces AI-based system optimizations that make thin and light mobile workstations perform better than ever.
*Support for MAX-Q technology varies by OEM system.
Certifications for leading professional software applications deliver a smooth and stable user experience across a wide variety of workflows, including animation, computer-aided design (CAD), simulation, rendering, and more.
Laptops with professional GPUs are easy to deploy, use, and manage across organizations with enterprise support, long lifecycle availability of the GPU, a robust suite of software tools for desktop management, multi-display modes, and IT management.
Enterprise drivers are continually tuned and tested for software compatibility and stability. Professional RTX GPUs undergo rigorous testing at the hardware and software levels to deliver peak productivity across workflows.
Certifications and multi-display capabilities vary by OEM. Check with your OEM for support for specific features.
Find the right solution to tackle your most challenging design and visualization workflows from anywhere.
Select a partner below to view hardware models and GPU options.
GPU Specifications | Performance | Options | |||||||||||||
Laptop GPUs | NVIDIA CUDA® Processing Cores1 | NVIDIA RT Cores | NVIDIA Tensor Cores | GPU Memory | Peak Memory Bandwidth | Memory Type | Memory Interface | TGP Max Power Consumption2 | DisplayPort3 | PCIe Generation | Single Precision Floating-Point Performance (TFLOPS,Peak)4 | AI TOPS9 | Tensor Performance (TFLOPS, Peak)4,5 | NVIDIA MAX-Q Technology | NVENC / NVDEC6 |
NVIDIA RTX 5000 Ada Generation | 9,728 | 76 (3rd Gen) | 304 (4th Gen) | 16GB ECC7 | 576GB/s | GDDR6 | 256-bit | 80-175W | 1.4a | 4 | 42.6 | 682 | 681.8 | ||
NVIDIA RTX 4000 Ada Generation | 7,424 | 58 (3rd Gen) | 232 (4th Gen) | 12GB ECC7 | 432GB/s | GDDR6 | 192-bit | 60-175W | 1.4a | 4 | 33.6 | 538 | 538.0 | ||
NVIDIA RTX 3500 Ada Generation | 5,120 | 40 (3rd Gen) | 160 (4th Gen) | 12GB ECC7 | 432GB/s | GDDR6 | 192-bit | 60-140W | 1.4a | 4 | 23.0 | 369 | 368.6 | ||
NVIDIA RTX 3000 Ada Generation | 4,608 | 36 (3rd Gen) | 144 (4th Gen) | 8GB ECC7 | 256GB/s | GDDR6 | 128-bit | 35-140W | 1.4a | 4 | 19.9 | 319 | 318.6 | ||
NVIDIA RTX 2000 Ada Generation | 3,072 | 24 (3rd Gen) | 96 (4th Gen) | 8GB | 256GB/s | GDDR6 | 128-bit | 35-140W | 1.4a | 4 | 14.5 | 232 | 231.6 | ||
NVIDIA RTX 1000 Ada Generation | 2,560 | 20 (3rd Gen) | 80 (4th Gen) | 6GB | 192GB/s | GDDR6 | 96-bit | 35-140W | 1.4a | 4 | 12.1 | 193 | 193.0 | ||
NVIDIA RTX 500 Ada Generation | 2,048 | 16 (3rd Gen) | 64 (4th Gen) | 4GB | 128GB/s | GDDR6 | 64-bit | 35-60W | 1.4a | 4 | 9.2 | 154 | 147.4 | ||
NVIDIA RTX A5500 | 7,424 | 458 (2nd Gen) | 232 (3rd Gen) | 16GB ECC7 | 512GB/s | GDDR6 | 256-bit | 80-165W | 1.4a | 4 | 24.7 | 396 | 197.8 | ||
NVIDIA RTX A4500 | 5,888 | 46 (2nd Gen) | 184 (3rd Gen) | 16GB ECC7 | 512GB/s | GDDR6 | 256-bit | 80-140W | 1.4a | 4 | 18.5 | 297 | 148.4 | ||
NVIDIA RTX A3000 12GB | 4,096 | 32 (2nd Gen) | 128 (3rd Gen) | 12GB ECC7 | 336GB/s | GDDR6 | 192-bit | 60-130W | 1.4a | 4 | 14.1 | 226 | 113.0 | ||
NVIDIA RTX A2000 8GB | 2,560 | 20 (2nd Gen) | 80 (3rd Gen) | 8GB | 224GB/s | GDDR6 | 128-bit | 35-95W | 1.4a | 4 | 9.3 | 149 | 74.3 | ||
NVIDIA RTX A1000 6GB | 2,560 | 20 (2nd Gen) | 80 (3rd Gen) | 6GB | 168GB/s | GDDR6 | 96-bit | 35-95W | 1.4a | 4 | 9.3 | 149 | 74.6 | ||
NVIDIA RTX A500 | 2,048 | 16 (2nd Gen) | 64 (3rd Gen) | 4GB | 112GB/s | GDDR6 | 64-bit | 20-60W | 1.4a | 4 | 78 | 120 | 568 |
1. CUDA parallel processing cores cannot be compared between GPU generations due to several important architectural differences that exist between streaming multiprocessor designs. 2.Maximum possible power consumption including the Dynamic Boost algorithm. For system specific GPU TGP, please consult your OEM/solution provider. 3. Display support varies by system-level implementation. Check with your workstation OEM vendor for system specific configurations. Adaptors available for DVI-SL, DVI-DL, HDMI, and VGA. 4.Peak rates are based on GPU boost clock. 5.Effective TFLOPS using the sparsity feature. NVIDIA Ada Lovelace architecture using FP8 matrix multiply with FP16 or FP32 accumulate; NVIDIA Ampere architecture using FP16 matrix multiply with FP16 or FP32 accumulate. 6.Number of NVENC and NVDEC may vary by GPU. GPU specific details can be found here: https://developer.nvidia.com/video-encode-and-decode-gpu-support-matrix-new 7.Ensures data integrity and reliability by eliminating soft errors on direct random-access memory (DRAM) only. 8. Peak FLOP and display support for NVIDIA RTX A500 Laptop GPU varies by system configuration. Check with your OEM system vendor to confirm which specification is supported. 9. INT8 TOPS with Sparsity (up to)