GPU Comparison
GEFORCE
NVIDIA CMP 90HX
CORE STATE
GA102
VRAM
10 GB
CLOCK SPEED
1710 MHz
TDP
320 W
BUS WIDTH
320 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
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
geekbench_opencl
geekbench_vulkan
Analysis: NVIDIA CMP 90HX vs NVIDIA L4
When gaming capability is remarkably similarly competitive, this matchup between NVIDIA's NVIDIA L4 graphics and NVIDIA CMP 90HX (NVIDIA) grows increasingly nuanced. These options exchange leads over diverse scenarios. The total picture is one of notable equality. Not one stands as a definite champion. This selection relies on personal needs.
When buyers torn between NVIDIA's NVIDIA L4 graphics and NVIDIA CMP 90HX (NVIDIA), rest certain that either selection achieves matching visual performance. The test data demonstrates zero obvious leader. Make your choice on alternative considerations and experience excellent rendering capability either way. The two are champions in their respective sense. Go with assuredly.
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 90HX
L4
Core Specs
Shading Units
6,400
7,424
+16.0%
Shaders
6,400
7,424
+16.0%
TMUs
200
240
+20.0%
ROPs
80
80
0.0%
SM Count
50
60
+20.0%
Clocks
Base Clock
1500 MHz
795 MHz
Boost Clock
1710 MHz
2040 MHz
Memory Clock
1188 MHz
19 Gbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
10 GB
24 GB
VRAM (MB)
10,240
24,576
+140.0%
Memory Type
GDDR6X
GDDR6
Memory Bus
320 bit
192 bit
Bandwidth
760.3 GB/s
300.1 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
5 MB
48 MB
Performance
Pixel Rate
136.8 GPixel/s
163.2 GPixel/s
Texture Rate
342.0 GTexel/s
489.6 GTexel/s
FP32 (TFLOPS)
21.89 TFLOPS
30.29 TFLOPS
FP64 (TFLOPS)
342.0 GFLOPS (1:64)
473.3 GFLOPS (1:64)
FP16 (TFLOPS)
21.89 TFLOPS (1:1)
30.29 TFLOPS (1:1)
AI/RT
RT Cores
50
60
+20.0%
Tensor Cores
200
240
+20.0%
Power
TDP
320 W
72 W
TDP (W)
320
72
-77.5%
Suggested PSU
700 W
250 W
Power Connectors
2x 8-pin
None
Architecture
Architecture
Ampere
Ada Lovelace
GPU Name
GA102
AD104
Generation
Mining GPUs
Server Ada
(Lxx)
Process Size
8 nm
5 nm
Transistors
28,300 million
35,800 million
Die Size
628 mm²
294 mm²
Foundry
Samsung
TSMC
Density
45.1M / 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
8.6
8.9
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
285 mm
11.2 inches
169 mm
6.7 inches
Height
112 mm
4.4 inches
56 mm
2.2 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
—
Server Ampere
Successor
—
Server Hopper