NVIDIA GeForce RTX 5070 Ti vs AMD Radeon RX 9070 XT Full Specs
8,960 Shaders 2.45GHz | 4,096 Shaders 2.97GHz |
16GB GDDR7896GB/s | 16GB GDDR6640GB/s |
·· 43.94 TFLOPS | ·· 48.66 TFLOPS |
Form Factor PCIe Card | Form Factor PCIe Card |
TDP 300W | TDP 304W |
Power Connectors 1x 16-Pin 12VHPWR - | Power Connectors - 2x 8-Pin |
GeForce RTX 5070 Ti1.41 PFLOPSFP4 Tensor Sparse
Radeon RX 9070 XT1.56 POPSINT4 Tensor SparseClock Speed ··· | Clock Speed ··· |
Peak OPS 1.41 PFLOPSFP4 Tensor Sparse | Peak OPS 1.56 POPSINT4 Tensor Sparse |
Tensor FP4 703 TFLOPSFP4 Tensor Sparse 1.41 PFLOPS | - |
Tensor FP8-16 351.5 TFLOPSFP8-16 Tensor Sparse 703 TFLOPSTensor FP8-32 175.8 TFLOPSFP8-32 Tensor Sparse 351.5 TFLOPS | Tensor FP8-16 194.6 TFLOPSFP8-16 Tensor Sparse 389.3 TFLOPSTensor FP8-32 194.6 TFLOPSFP8-32 Tensor Sparse 389.3 TFLOPS |
Tensor FP16-16 175.8 TFLOPSFP16-16 Tensor Sparse 351.5 TFLOPSTensor FP16-32 87.88 TFLOPSFP16-32 Tensor Sparse 175.8 TFLOPS | Tensor FP16-16 97.32 TFLOPSFP16-16 Tensor Sparse 194.6 TFLOPSTensor FP16-32 97.32 TFLOPSFP16-32 Tensor Sparse 194.6 TFLOPS |
BF16 43.94 TFLOPSTensor BF16 87.88 TFLOPSBF16 Tensor Sparse 175.8 TFLOPS | BF16 97.32 TFLOPSTensor BF16 97.32 TFLOPSBF16 Tensor Sparse 194.6 TFLOPS |
Tensor TF32 43.94 TFLOPS | Tensor TF32 - |
FP32 43.94 TFLOPS | FP32 48.66 TFLOPS |
FP64 686.6 GFLOPS | FP64 1.52 TFLOPS |
Tensor INT4 - | Tensor INT4 778.6 TOPS |
Tensor INT8 351.5 TOPS | Tensor INT8 389.3 TOPS |
Ray 133.3 TOPS | Ray - |
Pixel Rate 235.4 GPixel/s | Pixel Rate 380.2 GPixel/s |
Texture Rate 686.6 GTexel/s | Texture Rate 760.3 GTexel/s |
Shaders 8,960 Shaders | Shaders 4,096 Shaders |
TMUs 280 TMUs | TMUs 256 TMUs |
ROPs 96 ROPs | ROPs 128 ROPs |
Tensor Cores 280 T-Cores | Tensor Cores 128 T-Cores |
RT Cores 70 RT-Cores | RT Cores 64 RT-Cores |
SMs 70 SMs | CUs 64 CUs |
Base Clock 2.3GHz | Base Clock 2.4GHz |
Boost Clock 2.45GHz | Boost Clock 2.97GHz |
L2 Cache 65.5MB shared | L2 Cache 8.2MB shared |
L3 Cache - | L3 Cache 64MB shared |
L3 Bandwidth - | L3 Bandwidth 2.25TB/s |
16GB GDDR7 | 16GB GDDR6 |
Memory Bus 256-bit | Memory Bus 256-bit |
Memory Speed 28GT/s | Memory Speed 20GT/s |
Memory Bandwidth 896GB/s | Memory Bandwidth 640GB/s |
TDP 300W | TDP 304W |
Max Temp 88°C Max | Max Temp - |
Multi-Monitor 4 | Multi-Monitor 3 |
HDCP HDCP 2.3 | HDCP HDCP 2.3 |
3x DisplayPort 2.1 | 3x DisplayPort 2.1 |
1x HDMI 2.1 | 1x HDMI 2.1 |
Encoder Model 2x NVENC 9 | Encoder Model VCN 4.0 |
Decoder Model NVDEC 6 | Decoder Model VCN 4.0 |
Form Factor PCIe Card | Form Factor PCIe Card |
PCIe 2.1-Slots | PCIe 2.5-Slots |
Height 137 mm (5.39")Width 304 mm (11.97")Depth 42 mm (1.65") | Height 111 mm (4.37")Width 267 mm (10.51")Depth 50 mm (1.97") |
Cooling Open-Air 2x Fans | Cooling Open-Air 3x Fans |
Power Connectors 1x 16-Pin 12VHPWR | Power Connectors 2x 8-Pin |
Manufacturer | Manufacturer |
Chip Designer | Chip Designer |
Architecture | Architecture |
Family | Family |
Branding  | Branding  |
Codename NV193 | Codename - |
Chip Variant GB203-200-A1 | Chip Variant Navi 48 XL |
Market Segment Desktop | Market Segment Desktop |
Release Date Jan 6, 2025 | Release Date Jan 6, 2025 |
Foundry TSMC | Foundry TSMC |
Fabrication Node 4NP | Fabrication Node N4P |
Die Size 378mm² | Die Size 357mm² |
Transistor Count 45.6 Billion | Transistor Count 53.9 Billion |
Transistor Density 120.6 MTr/mm² | Transistor Density 151.2 MTr/mm² |
No images available
No images available