GPU Comparison
GEFORCE
NVIDIA 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
VS
GEFORCE
RTX A4000
CORE STATE
GA104
VRAM
16 GB
CLOCK SPEED
1560 MHz
TDP
140 W
BUS WIDTH
256 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
3dmark_3dmark_steel_nomad_dx12
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
L4
RTX A4000
Core Specs
Shading Units
7,424
6,144
-17.2%
Shaders
7,424
6,144
-17.2%
TMUs
240
192
-20.0%
ROPs
80
96
+20.0%
SM Count
60
48
-20.0%
Clocks
Base Clock
795 MHz
735 MHz
Boost Clock
2040 MHz
1560 MHz
Memory Clock
1563 MHz
12.5 Gbps effective
1750 MHz
14 Gbps effective
Memory
Memory Size
24 GB
16 GB
VRAM (MB)
24,576
16,384
-33.3%
Memory Type
GDDR6
GDDR6
Memory Bus
192 bit
256 bit
Bandwidth
300.1 GB/s
448.0 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
48 MB
4 MB
Performance
Pixel Rate
163.2 GPixel/s
149.8 GPixel/s
Texture Rate
489.6 GTexel/s
299.5 GTexel/s
FP32 (TFLOPS)
30.29 TFLOPS
19.17 TFLOPS
FP64 (TFLOPS)
473.3 GFLOPS (1:64)
299.5 GFLOPS (1:64)
FP16 (TFLOPS)
30.29 TFLOPS (1:1)
19.17 TFLOPS (1:1)
AI/RT
RT Cores
60
48
-20.0%
Tensor Cores
240
192
-20.0%
Power
TDP
72 W
140 W
TDP (W)
72
140
+94.4%
Suggested PSU
250 W
300 W
Power Connectors
None
1x 6-pin
Architecture
Architecture
Ada Lovelace
Ampere
GPU Name
AD104
GA104
Generation
Server Ada
(Lxx)
Workstation Ampere
(Ax000)
Process Size
5 nm
8 nm
Transistors
35,800 million
17,400 million
Die Size
294 mm²
392 mm²
Foundry
TSMC
Samsung
Density
121.8M / mm²
44.4M / 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
8.6
Shader Model
6.8
6.8
Physical
Slot Width
Single-slot
Single-slot
Length
169 mm
6.7 inches
241 mm
9.5 inches
Height
56 mm
2.2 inches
112 mm
4.4 inches
Outputs
No outputs
4x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Other
Production
Active
End-of-life
Predecessor
Server Ampere
Quadro Turing
Successor
Server Hopper
Workstation Ada