NVIDIA H100 SXM5 80 GB vs AMD Radeon 8060S
GPU · Specs Compare
Graphics Card
Release Date
Oct 2022
Jan 2025
Generation
Server Hopper
Navi Mobile
Type
AI GPU
Integrated
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1590 MHz
1295 MHz
Boost Clock
1980 MHz
2900 MHz
Memory Clock
1313 MHz
System Shared
Memory
Memory Size
80GB
System Shared
Memory Type
HBM3
System Shared
Memory Bus
5120bit
System Shared
Bandwidth
3.36TB/s
System Dependent
Render Config
SM Count
132
—
Shading Units
16896
2560
TMUs
528
160
ROPs
24
64
Tensor Cores
528
—
L1 Cache
256 KB (per SM)
—
L2 Cache
50 MB
8 MB
Compute Units
—
40
RT Cores
—
40
L3 Cache
—
64 MB
Theoretical Performance
Pixel Rate
47.52 GPixel/s
185.6 GPixel/s
Texture Rate
1045 GTexel/s
464.0 GTexel/s
FP16 (half)
267.6 TFLOPS
29.70 TFLOPS
FP32 (float)
66.91 TFLOPS
14.85 TFLOPS
FP64 (double)
33.45 TFLOPS
464.0 GFLOPS
Graphics Processor
GPU Name
GH100
Strix Halo
Architecture
Hopper
RDNA 3.5
Foundry
TSMC
TSMC
Process Size
5 nm
4 nm
Transistors
80 billion
Unknown
Die Size
814 mm²
308 mm²
Board Design
TDP
700W
55W
Suggested PSU
1100 W
—
Outputs
No outputs
Portable Device Dependent
Power Connectors
None
None
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.3
CUDA
9.0
—
Shader Model
N/A
6.8
Benchmark
3DMark Time Spy
—
9,863
3DMark Time Spy Extreme
—
4,878
Blender
—
1,248
▲ Specs Compare
Data sourced from official specifications and benchmark tests.