 Unterschiede hervorheben |  Nvidia RTX 4000 Ada mit 20 GB GDDR6 ECC-RAM |
Nvidia RTX PRO 4000 Blackwell mit 24 GB GDDR7 ECC-RAM |
Nvidia RTX 4500 Ada mit 24 GB GDDR6 ECC-RAM |
Nvidia RTX PRO 4500 Blackwell mit 32 GB GDDR7 ECC-RAM |
Nvidia RTX 5000 Ada mit 32 GB GDDR6 ECC-RAM |
Nvidia RTX PRO 5000 Blackwell mit 48 GB GDDR7 ECC-RAM |
Nvidia RTX 6000 Ada mit 48 GB GDDR6 ECC-RAM |
Nvidia RTX PRO 6000 Blackwell Max-Q Workstation Edition mit 96 GB GDDR7 ECC-RAM |
| Chipsatz | RTX 4000 Ada | RTX PRO 4000 | RTX 4500 Ada | RTX PRO 4500 | RTX 5000 Ada | RTX PRO 5000 | RTX 6000 Ada | RTX PRO 6000 |
| GPU Architektur | Ada | Blackwell | Ada | Blackwell | Ada | Blackwell | Ada Lovelace | Blackwell Max-Q |
| Speicher | 20 GB | 24 GB | 24 GB | 32 GB | 32 GB | 48 GB | 48 GB | 96 GB |
| Speicherart | GDDR6 ECC | GDDR7 ECC | GDDR6 ECC | GDDR7 ECC | GDDR6 ECC | GDDR7 ECC | GDDR6 ECC | GDDR7 ECC |
| Speicheranbindung | 160 Bit | 192 Bit | 192 Bit | 256 Bit | 256 Bit | 384 Bit | 384 Bit | 512 Bit |
| Speicherbandbreite | 360 GB/s | 672 GB/s | 432 GB/s | 896 GB/s | 576 GB/s | 1344 GB/s | 960 GB/s | 1790 GB/s |
| GPU-Taktung | 1500 MHz | 2055 MHz | 2070 MHz | 2407 MHz | 1155 MHz | 2377 MHz | 915 MHz | 2280 MHz |
| CUDA / Streamprozessoren | 6144 | 8960 | 7680 | 10496 | 12800 | 14080 | 18176 | 24064 |
| Gleitkomma-Rechenleistung (FP32) | 26,73 TFLOPS | 36,83 TFLOPS | 39,60 TFLOPS | 50,53 TFLOPS | 65,31 TFLOPs | 66,94 TFLOPs | 91,06 TFLOPs | 109,7 TFLOPS |
| Steckplatz | PCIe 4.0 x16 | PCIe 5.0 x16 | PCIe 4.0 x16 | PCIe 5.0 x16 | PCIe 4.0 x16 | PCIe 5.0 x16 | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Slotbreite | 1 Slot | 1 Slot | 2 Slots | 2 Slots | 2 Slots | 2 Slots | 2 Slots | 2 Slots |
| Anschlüsse | 4x DP 1.4a | 4x DisplayPort 2.1b | 4x DP 1.4a | 4x DisplayPort 2.1b | 4x DP 1.4a | 4x DisplayPort 2.1b | 4x DP 1.4a + VirtualLink | 4x DisplayPort 2.1b |
| Kühlung | active | active | active | active | active | active | active | active |
| Verbrauch (Watt) | 130W | 140W | 210W | 200W | 250W | 300W | 300W | 300W |
| DirectX | 12_2 Ultimate | 12_2 Ultimate | 12_2 Ultimate | 12_2 Ultimate | 12_2 Ultimate | 12_2 Ultimate | 12_2 Ultimate | 12_2 Ultimate |
| Open-GL | 4.6 | 4.6 | 4.6 | 4.6 | 4.6 | 4.6 | 4.68 | 4.6 |
| Open-CL | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.4 | 1.3 | 1.4 | 1.3 | 1.4 | 1.3 | 1.4 |
| Shader Model | 6.7 | 6.8 | 6.7 | 6.8 | 6.7 | 6.8 | 6.7 | 6.8 |
| Max. Auflösung (Pixel) | 7680x4320 | 7680x4320 | 7680x4320 | 7680x4320 | 7680x4320 | 7680x4320 | 7680x4320 | 7680x4320 |
| Max. Anzahl Monitore | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 4 |
| Zusatzfunktionen | 48 RT Cores, 192 Tensor Cores, CUDA, RTX IO, DirectCompute, GPUDirect, OpenCL, Mosaic, 2x encode/decode (+AV1) | 770 AI TOPS, 70 RT Cores, 96 ROPs, 280 Tensor Cores (5th Gen), DLSS 4, FP4, NVIDIA AI, RTX IO, DirectCompute, GPUDirect, OpenCL, 2x AV1 encode (9th Gen) and decode (6th Gen), VP11 | 60 RT Cores, 240 Tensor Cores, CUDA, RTX IO, DirectCompute, GPUDirect, OpenCL, Mosaic, 2x encode/decode (+AV1) | 1687 AI TOPS, 82 RT Cores, 112 ROPs, 328 Tensor Cores (5th Gen), DLSS 4, FP4, NVIDIA AI, RTX IO, DirectCompute, GPUDirect, OpenCL, 2x AV1 encode (9th Gen) and decode (6th Gen), VP11 | 100 RT Cores, 400 Tensor Cores, CUDA, NVIDIA vPC/vApps/vWS, RTX IO, DirectCompute, GPUDirect, OpenCL, Mosaic, 2x encode/decode (+AV1) | 2064 AI TOPS, 110 RT Cores, 176 ROPs, 440 Tensor Cores (5th Gen), DLSS 4, FP4, NVIDIA AI, RTX IO, DirectCompute, GPUDirect, OpenCL, 3x AV1 encode (9th Gen) and decode (6th Gen), VP11, MIG (1x48GB, 2x2 | NVIDIA vPC/vApps/vWS, NVIDIA vGPU, NVIDIA GPUDirect, NVIDIA GPU Boost, NVIDIA RTX IO, NVIDIA Mosaic, AV1 encode and decode | 3511 AI TOPS, 188 RT Cores, 192 ROPs, 752 Tensor Cores (5th Gen), DLSS 4, FP4, NVIDIA AI, RTX IO, DirectCompute, GPUDirect, OpenCL, 4x AV1 encode (9th Gen) and decode (6th Gen), VP11, MIG (1x96GB, 2x4 |
