NVIDIA L40S vs NVIDIA RTX PRO 6000 Blackwell Server
GPU · Specs Compare
Graphics Card
Release Date
Oct 2022
Mar 2025
Generation
Server Ada
Server Blackwell
Type
Professional
Professional
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1065 MHz
1590 MHz
Boost Clock
2520 MHz
2617 MHz
Memory Clock
2250 MHz
1750 MHz
Memory
Memory Size
48GB
96GB
Memory Type
GDDR6
GDDR7
Memory Bus
384bit
512bit
Bandwidth
864.0GB/s
1.79TB/s
Render Config
SM Count
142
188
Shading Units
18176
24064
TMUs
568
752
ROPs
192
192
Tensor Cores
568
752
RT Cores
142
188
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
48 MB
128 MB
Theoretical Performance
Pixel Rate
483.8 GPixel/s
502.5 GPixel/s
Texture Rate
1431.4 GTexel/s
1968.0 GTexel/s
FP16 (half)
91.61 TFLOPS
126.0 TFLOPS
FP32 (float)
91.61 TFLOPS
126.0 TFLOPS
FP64 (double)
1431.4 GFLOPS
1.968 TFLOPS
Graphics Processor
GPU Name
AD102
GB202
GPU Variant
AD102-896-A1
—
Architecture
Ada Lovelace
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
5 nm
Transistors
76.3 billion
92.2 billion
Die Size
609 mm²
750 mm²
Board Design
TDP
350W
600W
Suggested PSU
750 W
1000 W
Outputs
4x DisplayPort 1.4a
4x DisplayPort 2.1b
Power Connectors
1x 16-pin
1x 16-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.4
1.4
CUDA
8.9
12.0
Shader Model
6.9
6.9
Benchmark
Blender
9,239
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.