NVIDIA RTX 6000 ADA generation

Description:

• GPU memory: 48 GB GDDR6 ECC
• Architecture: NVIDIA Ada Lovelace
• Manufacturing process: 4 nm NVIDIA Custom Process (TSMC)
• Transistors: 76.3 billion
• Die size: 608.4 mm²
• CUDA cores: 18,176
• Tensor Cores: 568 (4th Generation)
• RT Cores: 142 (3rd Generation)
• Single-Precision performance: 91.1 TFLOPS*
• RT Core performance: 210.6 TFLOPS*
• Tensor performance: 1,457.0 TFLOPS**
• Memory interface: 384-bit
• Memory bandwidth: 960 GB/s
• vGPU profiles: 1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB
• Max. simultaneous displays: 4× 4,096 × 2,160 @ 120 Hz / 4× 5,120 × 2,880 @ 60 Hz / 2× 7,680 × 4,320 @ 60 Hz
• System interface: PCI Express 4.0 x16
• NVENC / NVDEC: 3× / 3× (+ AV1 Encode & Decode)
• NVLink: Not supported
• Frame Lock: compatible (with Quadro Sync II)
• Power consumption: 300 W
• Power connector: 1× PCIe CEM5 16-pin
• Thermal solution: Active blower
• Form factor: Dual slot, FHFL, 4.4" × 10.5"
• Product weight: 1,180 g
• Graphics API: DirectX 12, Shader Model 6.7, OpenGL 4.6, Vulkan 1.3
• Compute API: CUDA 12.2, OpenCL 3.0, DirectCompute

* Peak rates based on GPU Boost Clock ** Effective FP8 TFLOPS using the sparsity feature