GPU Comparison
GEFORCE
NVIDIA A10M
CORE STATE
GA102
VRAM
20 GB
CLOCK SPEED
1635 MHz
TDP
150 W
BUS WIDTH
320 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
—
VS
GEFORCE
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
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
A10M
RTX 4090 D
Core Specs
Shading Units
7,168
14,592
+103.6%
Shaders
7,168
14,592
+103.6%
TMUs
224
456
+103.6%
ROPs
80
176
+120.0%
SM Count
56
114
+103.6%
Clocks
Base Clock
975 MHz
2280 MHz
Boost Clock
1635 MHz
2520 MHz
Memory Clock
1563 MHz
12.5 Gbps effective
1313 MHz
21 Gbps effective
Memory
Memory Size
20 GB
24 GB
VRAM (MB)
20,480
24,576
+20.0%
Memory Type
GDDR6
GDDR6X
Memory Bus
320 bit
384 bit
Bandwidth
500.2 GB/s
1.01 TB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
6 MB
72 MB
Performance
Pixel Rate
130.8 GPixel/s
443.5 GPixel/s
Texture Rate
366.2 GTexel/s
1,149.1 GTexel/s
FP32 (TFLOPS)
23.44 TFLOPS
73.54 TFLOPS
FP64 (TFLOPS)
732.5 GFLOPS (1:32)
1,149.1 GFLOPS (1:64)
FP16 (TFLOPS)
23.44 TFLOPS (1:1)
73.54 TFLOPS (1:1)
AI/RT
RT Cores
56
114
+103.6%
Tensor Cores
224
456
+103.6%
Power
TDP
150 W
425 W
TDP (W)
150
425
+183.3%
Suggested PSU
450 W
800 W
Power Connectors
8-pin EPS
1x 16-pin
Architecture
Architecture
Ampere
Ada Lovelace
GPU Name
GA102
AD102
Generation
Server Ampere
(Axx)
GeForce 40
Process Size
8 nm
5 nm
Transistors
28,300 million
76,300 million
Die Size
628 mm²
609 mm²
Foundry
Samsung
TSMC
Density
45.1M / mm²
125.3M / 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
8.6
8.9
Shader Model
6.8
6.8
Physical
Slot Width
Single-slot
Triple-slot
Length
267 mm
10.5 inches
304 mm
12 inches
Height
112 mm
4.4 inches
137 mm
5.4 inches
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Other
Launch Price
—
1,599 USD
Production
End-of-life
End-of-life
Predecessor
Tesla Turing
GeForce 30
Successor
Server Ada
GeForce 50