NVIDIA RTX 4000 SFF ADA generation

Description:

• GPU memory: 20 GB GDDR6 ECC
• Architecture: NVIDIA Ada Lovelace
• CUDA cores: 6,144
• Tensor Cores: 192 (4th Generation)
• RT Cores: 48 (3rd Generation)
• Single-Precision performance: 19.2 TFLOPS*
• RT Core performance: 44.3 TFLOPS*
• Tensor performance: 306.8 TFLOPS**
• Memory interface: 160-bit
• Memory bandwidth: 320 GB/s
• 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: 2× / 2× (+ AV1 Encode & Decode)
• NVLink: Not supported
• Power consumption: 70 W
• Power connector: None (slot powered)
• Thermal solution: Active
• Form factor: Dual slot, LP, 2.7" × 6.6"
• Graphics API: DirectX 12, Shader Model 6.6, OpenGL 4.6, Vulkan 1.3
• Compute API: CUDA 11.6, OpenCL 3.0, DirectCompute

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