NVIDIA AD102 Graphics Processing Unit (GPU)

Specs based on NVIDIA L40S
Overview
Manufacturer
NVIDIA
Graphics Processing Unit
Architecture
Ada
Fabrication Process
4 nm
Die Size
608 mm2
Transistors Count
76.3B
Transistors Density
125.5M TRAN/mm2
Tensor Cores
568
RT Cores
142
CUDAs
18176
SM
142
TMUs
568
ROPs
192
Clocks
Boost Clock
2520 MHz
Memory Configuration
Memory Size
49152 MB
Memory Type
GDDR6
Memory Bus Width
384-bit
Memory Bandwidth
0.0 GB/s
Performance
Pixel Fillrate
483.8 GPixels/s
Texture Fillrate
1.4 TTexel/s
SPFP Performance
91.6 TFLOPS
Performance per W
261.7 GFLOPS/W
Performance per mm2
150.7 GFLOPS/mm2
Physical
Interface
PCI-Express 4.0 x16
Typical Thermal Design Power
350 W
SLI Support
2-way
API Support
DirectX
12.2
Vulkan
1.2
OpenGL
4.6
OpenCL
3.0




 ModelGPU ModelUnified CoresBoost ClockMemory ClockMemory Config.
NVIDIA RTX 6000 ADA AD102
 
18176
 
2506 MHz
 
20 Gbps
 
48 GB G6 384b
NVIDIA L40 AD102-895/895A
 
18176
 
2490 MHz
-
 
48 GB G6 384b
NVIDIA L40S AD102-895/895A
 
18176
 
2520 MHz
-
 
48 GB G6 384b
NVIDIA GeForce RTX 4090 AD102-300/301
 
16384
 
2520 MHz
 
21 Gbps
 
24 GB G6X 384b
NVIDIA GeForce RTX 4090D AD102-250
 
14592
 
2520 MHz
 
21 Gbps
 
24 GB G6X 384b
NVIDIA RTX 5880 ADA AD102
 
14080
 
2460 MHz
 
20 Gbps
 
48 GB G6 384b
NVIDIA RTX 5000 ADA AD102
 
12800
 
2598 MHz
 
18 Gbps
 
32 GB G6 256b