NVIDIA RTX 6000 Ada vs NVIDIA H100 NVL 94 GB
GPU · Specs Compare
Graphics Card
Release Date
Dec 2022
Mar 2023
Generation
Quadro Ada
Server Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
915 MHz
1080 MHz
Boost Clock
2505 MHz
1785 MHz
Memory Clock
2500 MHz
1313 MHz
Memory
Memory Size
48GB
94GB
Memory Type
GDDR6
HBM3
Memory Bus
384bit
6016bit
Bandwidth
960.0GB/s
3.95TB/s
Render Config
SM Count
142
132
Shading Units
18176
16896
TMUs
568
528
ROPs
192
24
Tensor Cores
568
528
RT Cores
142
—
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
96 MB
50 MB
Theoretical Performance
Pixel Rate
481.0 GPixel/s
42.84 GPixel/s
Texture Rate
1423 GTexel/s
942.5 GTexel/s
FP16 (half)
91.06 TFLOPS
241.3 TFLOPS
FP32 (float)
91.06 TFLOPS
60.32 TFLOPS
FP64 (double)
1423 GFLOPS
30.16 TFLOPS
Graphics Processor
GPU Name
AD102
GH100
GPU Variant
AD102
—
Architecture
Ada Lovelace
Hopper
Foundry
TSMC
TSMC
Process Size
5 nm
5 nm
Transistors
76.3 billion
80 billion
Die Size
609 mm²
814 mm²
Board Design
TDP
300W
400W
Suggested PSU
700 W
800 W
Outputs
4x DisplayPort 1.4a
No outputs
Power Connectors
1x 16-pin
8-pin EPS
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
8.9
9.0
Shader Model
6.8
N/A
Benchmark
3DMark Time Spy
26,240
—
3DMark Time Spy Extreme
12,629
—
3DMark Speed Way
8,028
—
Battlefield 5 1080p
200
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.