Architecture | NVIDIA Ada Lovelace Architecture |
Process Size | 4nm NVIDIA Custom Process | TSMC |
Die Size | 294.5 mm2 |
Transistors | 35.8 Billion |
CUDA Cores | 6144 |
Tensor Cores | 192 | Gen 4 |
RT Cores | 48 | Gen 3 |
FP32 Performance1 | 19.2 TFLOPS |
Tensor Performance1 | 306.8 TFLOPS2 |
RT Core Performance1 | 44.3 TFLOPS |
GPU Memory | 20 GB GDDR6 ECC |
Memory Interface | 160-bit |
Memory Bandwidth | 320 GB/s |
Display Connectors | mDP 1.4a (4)3 |
Graphics Bus | PCI Express 4.0 x16 |
Form Factor | 2.7” H x 6.6”L | Low Profile Dual Slot |
Thermal Solution | Active Fansink |
AR/MR/VR/XR Capable | Yes |
NVIDIA 3D Vision and 3D Vision Pro | Support via Optional 3-pin mini-DIN |
Frame Lock | Compatible with NVIDIA Quadro Sync II |
Maximum Power Consumption | 70W | No Auxiliary Power Required |
NVENC | NVDEC | 2x | 2x | Includes AV1 encode and Decode |
NVIDIA Ada Lovelace Architecture
NVIDIA RTX 4000 SFF Ada 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.