GeForce RTX 3060 Ti GDDR6X vs H100 SXM5 94 GB
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3060 Ti GDDR6X and 94GB VRAM H100 SXM5 94 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3060 Ti GDDR6X 's Advantages
Lower TDP (225W vs 700W)
H100 SXM5 94 GB 's Advantages
Boost Clock has increased by 19% (1980MHz vs 1665MHz)
More VRAM (94GB vs 8GB)
Larger VRAM bandwidth (3.36TB/s vs 608.3GB/s)
12032 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3060 Ti GDDR6X
16200
H100 SXM5 94 GB
+313%
66910
Graphics Card
Oct 2022
Release Date
Mar 2023
GeForce 30
Generation
Server Hopper
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1410 MHz
Base Clock
1350 MHz
1665 MHz
Boost Clock
1980 MHz
1188 MHz
Memory Clock
1313 MHz
Memory
8GB
Memory Size
94GB
GDDR6X
Memory Type
HBM3
256bit
Memory Bus
5120bit
608.3GB/s
Bandwidth
3.36TB/s
Render Config
38
SM Count
132
4864
Shading Units
16896
152
TMUs
528
80
ROPs
24
152
Tensor Cores
528
38
RT Cores
-
128 KB (per SM)
L1 Cache
256 KB (per SM)
4 MB
L2 Cache
50 MB
Theoretical Performance
133.2 GPixel/s
Pixel Rate
47.52 GPixel/s
253.1 GTexel/s
Texture Rate
1045 GTexel/s
16.20 TFLOPS
FP16 (half)
267.6 TFLOPS
16.20 TFLOPS
FP32 (float)
66.91 TFLOPS
253.1 GFLOPS
FP64 (double)
33.45 TFLOPS
Board Design
225W
TDP
700W
550 W
Suggested PSU
1100 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 12-pin
Power Connectors
8-pin EPS
Graphics Processor
GA104
GPU Name
GH100
GA104-202-A1
GPU Variant
-
Ampere
Architecture
Hopper
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
17.4 billion
Transistors
80 billion
392 mm²
Die Size
814 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.6
CUDA
9.0
6.7
Shader Model
N/A
