GPU Comparison
GEFORCE
NVIDIA L40
CORE STATE
AD102
VRAM
48 GB
CLOCK SPEED
2490 MHz
TDP
300 W
BUS WIDTH
384 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2022
VS
GEFORCE
RTX PRO 2000 Blackwell
CORE STATE
GB206
VRAM
16 GB
CLOCK SPEED
1957 MHz
TDP
70 W
BUS WIDTH
128 bit
ARCHITECTURE
Blackwell 2.0
PROCESS
5 nm
LAUNCH DATE
2025
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
3dmark_3dmark_steel_nomad_dx12
Analysis: NVIDIA L40 vs NVIDIA RTX PRO 2000 Blackwell
Looking at the test numbers for NVIDIA L40 from NVIDIA and NVIDIA RTX PRO 2000 Blackwell by NVIDIA, a trend of close capability emerges. None of the card dominates steadily over all titles. This trading of leads implies underlying parity. Users have a genuine selection here. The two cards provide solid graphics capability.
When all is said and done: NVIDIA L40 from NVIDIA and NVIDIA RTX PRO 2000 Blackwell by NVIDIA are tightly matched. No earns a definite endorsement over the alternative. Allow availability and software preferences inform your concluding decision. The two graphics cards will satisfy you capably. It's a no-lose choice.
DETAILED SPECIFICATIONS
SPECIFICATION
L40
RTX PRO 2000 Blackwell
Core Specs
Shading Units
18,176
4,352
-76.1%
Shaders
18,176
4,352
-76.1%
TMUs
568
136
-76.1%
ROPs
192
64
-66.7%
SM Count
142
34
-76.1%
Clocks
Base Clock
735 MHz
982 MHz
Boost Clock
2490 MHz
1957 MHz
Memory Clock
2250 MHz
18 Gbps effective
1125 MHz
18 Gbps effective
Memory
Memory Size
48 GB
16 GB
VRAM (MB)
49,152
16,384
-66.7%
Memory Type
GDDR6
GDDR7
Memory Bus
384 bit
128 bit
Bandwidth
864.0 GB/s
288.0 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
96 MB
32 MB
Performance
Pixel Rate
478.1 GPixel/s
125.2 GPixel/s
Texture Rate
1,414.3 GTexel/s
266.2 GTexel/s
FP32 (TFLOPS)
90.52 TFLOPS
17.03 TFLOPS
FP64 (TFLOPS)
1,414.3 GFLOPS (1:64)
266.2 GFLOPS (1:64)
FP16 (TFLOPS)
90.52 TFLOPS (1:1)
17.03 TFLOPS (1:1)
AI/RT
RT Cores
142
34
-76.1%
Tensor Cores
568
136
-76.1%
Power
TDP
300 W
70 W
TDP (W)
300
70
-76.7%
Suggested PSU
700 W
250 W
Power Connectors
1x 16-pin
None
Architecture
Architecture
Ada Lovelace
Blackwell 2.0
GPU Name
AD102
GB206
Generation
Server Ada
(Lxx)
Blackwell PRO W
(x000)
Process Size
5 nm
5 nm
Transistors
76,300 million
21,900 million
Die Size
609 mm²
181 mm²
Foundry
TSMC
TSMC
Density
125.3M / mm²
121.0M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.9
12.0
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
167 mm
6.6 inches
Height
111 mm
4.4 inches
69 mm
2.7 inches
Outputs
4x DisplayPort 1.4a
4x mini-DisplayPort 2.1b
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x8
Other
Production
End-of-life
Active
Predecessor
Server Ampere
Workstation Ada
Successor
Server Hopper
—