L20 vs H200 NVL
We compared two Desktop platform GPUs: 48GB VRAM L20 and 141GB VRAM H200 NVL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
L20 's Advantages
Boost Clock has increased by 41% (2520MHz vs 1785MHz)
Lower TDP (275W vs 600W)
H200 NVL 's Advantages
Released 1 years late
More VRAM (141GB vs 48GB)
Larger VRAM bandwidth (4.89TB/s vs 864.0GB/s)
5120 additional rendering cores
Score
Benchmark
FP32 (float)
L20
59350
H200 NVL
+1%
60320
Graphics Card
Nov 2023
Release Date
Nov 2024
Tesla Ada
Generation
Server Hopper
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1440 MHz
Base Clock
1365 MHz
2520 MHz
Boost Clock
1785 MHz
2250 MHz
Memory Clock
1593 MHz
Memory
48GB
Memory Size
141GB
GDDR6
Memory Type
HBM3e
384bit
Memory Bus
6144bit
864.0GB/s
Bandwidth
4.89TB/s
Render Config
92
SM Count
132
11776
Shading Units
16896
368
TMUs
528
128
ROPs
24
368
Tensor Cores
528
92
RT Cores
-
128 KB (per SM)
L1 Cache
256 KB (per SM)
96 MB
L2 Cache
50 MB
Theoretical Performance
322.6 GPixel/s
Pixel Rate
42.84 GPixel/s
927.4 GTexel/s
Texture Rate
942.5 GTexel/s
59.35 TFLOPS
FP16 (half)
241.3 TFLOPS
59.35 TFLOPS
FP32 (float)
60.32 TFLOPS
927.4 GFLOPS
FP64 (double)
30.16 TFLOPS
Board Design
275W
TDP
600W
600 W
Suggested PSU
1000 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
8-pin EPS
Graphics Processor
AD102
GPU Name
GH100
AD102
GPU Variant
-
Ada Lovelace
Architecture
Hopper
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
76.3 billion
Transistors
80 billion
609 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
8.9
CUDA
9.0
6.7
Shader Model
N/A
