NVIDIA Rubin GPU vs AMD Zhongshan Subor Z+ GPU
GPU · Specs Compare
Graphics Card
Release Date
Jan 2026
Aug 2018
Generation
Server Rubin
Console GPU
Type
Desktop
Game console
Bus Interface
PCIe 6.0 x16
—
Clock Speeds
Base Clock
700 MHz
—
Boost Clock
2267 MHz
—
Memory Clock
2695 MHz
1200 MHz
Memory
Memory Size
288GB
8GB
Memory Type
HBM4
GDDR5
Memory Bus
16384bit
256bit
Bandwidth
22.1TB/s
153.6GB/s
Render Config
SM Count
224
—
Shading Units
28672
1536
TMUs
896
96
ROPs
24
32
Tensor Cores
896
—
L1 Cache
256 KB (per SM)
—
L2 Cache
128 MB
—
Compute Units
—
24
Theoretical Performance
Pixel Rate
54.41 GPixel/s
41.60 GPixel/s
Texture Rate
2031.2 GTexel/s
124.8 GTexel/s
FP16 (half)
260.0 TFLOPS
7.987 TFLOPS
FP32 (float)
130.0 TFLOPS
3.994 TFLOPS
FP64 (double)
32.50 TFLOPS
249.6 GFLOPS
Graphics Processor
GPU Name
GR100
Fenghuang
Architecture
Rubin
GCN 5.0
Foundry
TSMC
TSMC
Process Size
3 nm
14 nm
Transistors
336 billion
Unknown
Die Size
1456 mm²
397 mm²
GPU Variant
—
Zhongshan Subor
Board Design
TDP
2300W
100W
Suggested PSU
2700 W
—
Outputs
No outputs
No outputs
Graphics Features
DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.2
CUDA
10.7
—
Shader Model
N/A
6.2
▲ Specs Compare
Data sourced from official specifications and benchmark tests.