AMD Radeon Pro SSG Vega vs NVIDIA GeForce RTX 2070 Super Max-Q Full Specs
4,096 Shaders 1.5GHz | 2,560 Shaders 1.16GHz |
16GB HBM2483.8GB/s | 8GB GDDR6384GB/s |
·· 12.29 TFLOPS | ·· 5.91 TFLOPS |
Form Factor PCIe Card | Form Factor Soldered |
TDP 230W | TDP 80W |
Power Connectors 1x 8-Pin 1x 6-Pin | Power Connectors - |
Radeon Pro SSG Vega24.58 TFLOPSFP16
GeForce RTX 2070 Super Max-Q189.2 TOPSINT4 TensorClock Speed ··· | Clock Speed ··· |
Peak OPS 24.58 TFLOPSFP16 | Peak OPS 189.2 TOPSINT4 Tensor |
- | Tensor FP16-16 47.31 TFLOPSTensor FP16-32 23.65 TFLOPS |
- | Tensor BF16 23.65 TFLOPS |
Tensor TF32 - | Tensor TF32 23.65 TFLOPS |
FP32 12.29 TFLOPS | FP32 5.91 TFLOPS |
FP64 768 GFLOPS | FP64 184.8 GFLOPS |
Tensor INT4 - | Tensor INT4 189.2 TOPS |
- | Tensor INT8 94.62 TOPS |
Ray - | Ray 17.84 TOPS |
Pixel Rate 96 GPixel/s | Pixel Rate 73.9 GPixel/s |
Texture Rate 384 GTexel/s | Texture Rate 184.8 GTexel/s |
Shaders 4,096 Shaders | Shaders 2,560 Shaders |
TMUs 256 TMUs | TMUs 160 TMUs |
ROPs 64 ROPs | ROPs 64 ROPs |
Tensor Cores - | Tensor Cores 320 T-Cores |
RT Cores - | RT Cores 40 RT-Cores |
CUs 64 CUs | SMs 40 SMs |
Base Clock 1.44GHz | Base Clock 930MHz |
Boost Clock 1.5GHz | Boost Clock 1.16GHz |
L2 Cache 4.1MB shared | L2 Cache 4.1MB shared |
16GB HBM2 | 8GB GDDR6 |
Memory Bus 2048-bit | Memory Bus 256-bit |
Memory Speed 1.9GT/s | Memory Speed 12GT/s |
Memory Bandwidth 483.8GB/s | Memory Bandwidth 384GB/s |
TDP 230W | TDP 80W |
Multi-Monitor 3 | Multi-Monitor 3 |
HDCP HDCP 2.2 | HDCP HDCP 2.2 |
6x Mini DisplayPort 1.4 | - |
Encoder Model VCE 4.0 | Encoder Model NVENC 7 |
Decoder Model UVD 7.0 | Decoder Model NVDEC 4 |
Form Factor PCIe Card | Form Factor Soldered |
PCIe 2-Slots | PCIe - |
Height 111 mm (4.37")Width 267 mm (10.51")Depth 37 mm (1.46") | - |
Cooling Blower 1x Fan | Cooling Open-Air - |
Power Connectors 1x 8-Pin, 1x 6-Pin | Power Connectors - |
Manufacturer | Manufacturer |
Chip Designer | Chip Designer |
Architecture | Architecture |
Family | Family |
Branding  | Branding  |
Codename Greenland | Codename NV164 |
Chip Variant Vega 10 XL | Chip Variant TU104-150-KC-A1 |
Market Segment Workstation | Market Segment Laptop |
Release Date Aug 8, 2017 | Release Date Apr 2, 2020 |
Foundry GlobalFoundries | Foundry TSMC |
Fabrication Node 14LPP | Fabrication Node 12FFN |
Die Size 486mm² | Die Size 545mm² |
Transistor Count 12.5 Billion | Transistor Count 13.6 Billion |
Transistor Density 25.72 MTr/mm² | Transistor Density 24.95 MTr/mm² |
No images available
No images available
Laptops - | Laptops |