GPU Comparison
GEFORCE
NVIDIA GeForce RTX 4090 D
CORE STATE
AD102
VRAM
24 GB
CLOCK SPEED
2520 MHz
TDP
425 W
BUS WIDTH
384 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
VS
GEFORCE
L4
CORE STATE
AD104
VRAM
24 GB
CLOCK SPEED
2040 MHz
TDP
72 W
BUS WIDTH
192 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
RTX 4090 D
L4
Core Specs
Shading Units
14,592
7,424
-49.1%
Shaders
14,592
7,424
-49.1%
TMUs
456
240
-47.4%
ROPs
176
80
-54.5%
SM Count
114
60
-47.4%
Clocks
Base Clock
2280 MHz
795 MHz
Boost Clock
2520 MHz
2040 MHz
Memory Clock
1313 MHz
21 Gbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
24 GB
24 GB
VRAM (MB)
24,576
24,576
0.0%
Memory Type
GDDR6X
GDDR6
Memory Bus
384 bit
192 bit
Bandwidth
1.01 TB/s
300.1 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
72 MB
48 MB
Performance
Pixel Rate
443.5 GPixel/s
163.2 GPixel/s
Texture Rate
1,149.1 GTexel/s
489.6 GTexel/s
FP32 (TFLOPS)
73.54 TFLOPS
30.29 TFLOPS
FP64 (TFLOPS)
1,149.1 GFLOPS (1:64)
473.3 GFLOPS (1:64)
FP16 (TFLOPS)
73.54 TFLOPS (1:1)
30.29 TFLOPS (1:1)
AI/RT
RT Cores
114
60
-47.4%
Tensor Cores
456
240
-47.4%
Power
TDP
425 W
72 W
TDP (W)
425
72
-83.1%
Suggested PSU
800 W
250 W
Power Connectors
1x 16-pin
None
Architecture
Architecture
Ada Lovelace
Ada Lovelace
GPU Name
AD102
AD104
Generation
GeForce 40
Server Ada
(Lxx)
Process Size
5 nm
5 nm
Transistors
76,300 million
35,800 million
Die Size
609 mm²
294 mm²
Foundry
TSMC
TSMC
Density
125.3M / mm²
121.8M / 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
8.9
Shader Model
6.8
6.8
Physical
Slot Width
Triple-slot
Single-slot
Length
304 mm
12 inches
169 mm
6.7 inches
Height
137 mm
5.4 inches
56 mm
2.2 inches
Outputs
1x HDMI 2.13x DisplayPort 1.4a
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Other
Launch Price
1,599 USD
—
Production
End-of-life
Active
Predecessor
GeForce 30
Server Ampere
Successor
GeForce 50
Server Hopper