NVIDIA L20 vs NVIDIA B100
We compared two Desktop platform GPUs: 48GB VRAM L20 and 96GB VRAM B100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L20 's Advantages
Boost Clock has increased by 37% (2520MHz vs 1837MHz)
Lower TDP (275W vs 1000W)
NVIDIA B100 's Advantages
Released 1 years late
More VRAM (96GB vs 48GB)
Larger VRAM bandwidth (4.10TB/s vs 864.0GB/s)
5120 additional rendering cores
Score
Benchmark
FP32 (float)
L20
59.35 TFLOPS
B100
+4%
62.08 TFLOPS
Graphics Card
Nov 2023
Release Date
Nov 2024
Tesla Ada
Generation
Server Blackwell
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1440 MHz
Base Clock
1665 MHz
2520 MHz
Boost Clock
1837 MHz
2250 MHz
Memory Clock
2000 MHz
Memory
48GB
Memory Size
96GB
GDDR6
Memory Type
HBM3e
384bit
Memory Bus
4096bit
864.0GB/s
Bandwidth
4.10TB/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
44.09 GPixel/s
927.4 GTexel/s
Texture Rate
969.9 GTexel/s
59.35 TFLOPS
FP16 (half)
248.3 TFLOPS
59.35 TFLOPS
FP32 (float)
62.08 TFLOPS
927.4 GFLOPS
FP64 (double)
31.04 TFLOPS
Board Design
275W
TDP
1000W
600 W
Suggested PSU
1400 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
-
Graphics Processor
AD102
GPU Name
GB102
AD102
GPU Variant
-
Ada Lovelace
Architecture
Blackwell
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
76.3 billion
Transistors
104 billion
609 mm²
Die Size
Unknown
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
10.1
6.7
Shader Model
N/A
