NVIDIA GeForce RTX 4090 Ti vs NVIDIA RTX PRO 6000 Blackwell Server Full Specs
18,432 Shaders 2.63GHz | 24,064 Shaders 2.43GHz |
48GB GDDR6X1.01TB/s | 96GB GDDR71.79TB/s |
·· 96.77 TFLOPS | ·· 117 TFLOPS |
Form Factor PCIe Card | Form Factor PCIe Card |
TDP 600W | TDP 600W |
Power Connectors 1x 16-Pin 12VHPWR | Power Connectors 1x 16-Pin 12VHPWR |
Clock Speed ··· | Clock Speed ·· |
Peak OPS 3.1 POPSINT4 Tensor Sparse | Peak OPS 3.74 PFLOPSFP4 Tensor Sparse |
- | Tensor FP4 1.87 PFLOPSFP4 Tensor Sparse 3.74 PFLOPS |
Tensor FP8-16 774.1 TFLOPSFP8-16 Tensor Sparse 1.55 PFLOPSTensor FP8-32 387.1 TFLOPSFP8-32 Tensor Sparse 774.1 TFLOPS | Tensor FP8-16 935.6 TFLOPSFP8-16 Tensor Sparse 1.87 PFLOPSTensor FP8-32 467.8 TFLOPSFP8-32 Tensor Sparse 935.6 TFLOPS |
Tensor FP16-16 387.1 TFLOPSFP16-16 Tensor Sparse 774.1 TFLOPSTensor FP16-32 193.5 TFLOPSFP16-32 Tensor Sparse 387.1 TFLOPS | Tensor FP16-16 467.8 TFLOPSFP16-16 Tensor Sparse 935.6 TFLOPSTensor FP16-32 233.9 TFLOPSFP16-32 Tensor Sparse 467.8 TFLOPS |
BF16 96.77 TFLOPSTensor BF16 193.5 TFLOPSBF16 Tensor Sparse 387.1 TFLOPS | BF16 117 TFLOPSTensor BF16 233.9 TFLOPSBF16 Tensor Sparse 467.8 TFLOPS |
Tensor TF32 96.77 TFLOPS | Tensor TF32 117 TFLOPS |
FP32 96.77 TFLOPS | FP32 117 TFLOPS |
FP64 1.51 TFLOPS | FP64 1.83 TFLOPS |
Tensor INT4 1.55 POPS | Tensor INT4 - |
Tensor INT8 774.1 TOPS | Tensor INT8 935.6 TOPS |
Ray 223.7 TOPS | Ray 354.7 TOPS |
Pixel Rate 462 GPixel/s | Pixel Rate 466.6 GPixel/s |
Texture Rate 1.51 TTexel/s | Texture Rate 1.83 TTexel/s |
Shaders 18,432 Shaders | Shaders 24,064 Shaders |
TMUs 576 TMUs | TMUs 752 TMUs |
ROPs 176 ROPs | ROPs 192 ROPs |
Tensor Cores 576 T-Cores | Tensor Cores 752 T-Cores |
RT Cores 144 RT-Cores | RT Cores 188 RT-Cores |
SMs 144 SMs | SMs 188 SMs |
Base Clock 2.35GHz | Base Clock - |
Boost Clock 2.63GHz | Boost Clock 2.43GHz |
L2 Cache 98.3MB shared | L2 Cache 131.1MB shared |
48GB GDDR6X | 96GB GDDR7 |
Memory Bus 384-bit | Memory Bus 512-bit |
Memory Speed 21GT/s | Memory Speed 28GT/s |
Memory Bandwidth 1.01TB/s | Memory Bandwidth 1.79TB/s |
ECC No | ECC Yes |
TDP 600W | TDP 600W |
Max Temp 90°C Max | Max Temp - |
Multi-Monitor 4 | Multi-Monitor 4 |
HDCP HDCP 2.3 | HDCP HDCP 2.3 |
3x DisplayPort 1.4 | - |
1x HDMI 2.1 | - |
Encoder Model 2x NVENC 8 | Encoder Model 4x NVENC 9 |
Decoder Model NVDEC 5 | Decoder Model 4x NVDEC 6 |
Form Factor PCIe Card | Form Factor PCIe Card |
PCIe 3-Slots | PCIe 2-Slots |
Height 137 mm (5.39")Width 304 mm (11.97")Depth 61 mm (2.4") | Height 111.8 mm (4.4")Width 266.7 mm (10.5")Depth 40 mm (1.57") |
Cooling Open-Air 2x Fans | Cooling Passive - |
Power Connectors 1x 16-Pin 12VHPWR | Power Connectors 1x 16-Pin 12VHPWR |
Manufacturer | Manufacturer |
Chip Designer | Chip Designer |
Architecture | Architecture |
Family | Family |
Branding ![]() | Branding ![]() |
Codename NV182 | Codename NV192 |
Chip Variant AD102-200-A1 | Chip Variant GB202-250-A1 |
Market Segment Desktop | Market Segment Workstation |
Release Date - | Release Date Mar 18, 2025 |
Foundry TSMC | Foundry TSMC |
Fabrication Node 4N | Fabrication Node 4NP |
Die Size 608mm² | Die Size 762mm² |
Transistor Count 76.3 Billion | Transistor Count 92.2 Billion |
Transistor Density 125.4 MTr/mm² | Transistor Density 121.1 MTr/mm² |
No images available
No images available



