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
RTX 4000 SFF Ada Generation
CORE STATE
AD104
VRAM
20 GB
CLOCK SPEED
1560 MHz
TDP
70 W
BUS WIDTH
160 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
Analysis: NVIDIA CMP 90HX vs NVIDIA RTX 4000 SFF Ada Generation
Looking at the test figures for Radeon RTX 4000 and NVIDIA's NVIDIA CMP 90HX graphics, the story of matched frame rates develops. Not one option dominates consistently throughout all scenarios. This trading of victories indicates underlying equivalence. Consumers encounter a actual dilemma here. Each cards deliver capable rendering throughput.
When those undecided between Radeon RTX 4000 and NVIDIA's NVIDIA CMP 90HX graphics, be assured that each selection delivers equivalent gaming capability. The benchmark results demonstrates no clear winner. Form your choice on additional factors and experience solid gaming throughput in any case. The two are capable in their respective way. Pick comfortably.
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 90HX
RTX 4000 SFF Ada Generation
Core Specs
Shading Units
6,400
6,144
-4.0%
Shaders
6,400
6,144
-4.0%
TMUs
200
192
-4.0%
ROPs
80
64
-20.0%
SM Count
50
48
-4.0%
Clocks
Base Clock
1500 MHz
720 MHz
Boost Clock
1710 MHz
1560 MHz
Memory Clock
1188 MHz
19 Gbps effective
1750 MHz
14 Gbps effective
Memory
Memory Size
10 GB
20 GB
VRAM (MB)
10,240
20,480
+100.0%
Memory Type
GDDR6X
GDDR6
Memory Bus
320 bit
160 bit
Bandwidth
760.3 GB/s
280.0 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
99.84 GPixel/s
Texture Rate
342.0 GTexel/s
299.5 GTexel/s
FP32 (TFLOPS)
21.89 TFLOPS
19.17 TFLOPS
FP64 (TFLOPS)
342.0 GFLOPS (1:64)
299.5 GFLOPS (1:64)
FP16 (TFLOPS)
21.89 TFLOPS (1:1)
19.17 TFLOPS (1:1)
AI/RT
RT Cores
50
48
-4.0%
Tensor Cores
200
192
-4.0%
Power
TDP
320 W
70 W
TDP (W)
320
70
-78.1%
Suggested PSU
700 W
250 W
Power Connectors
2x 8-pin
None
Architecture
Architecture
Ampere
Ada Lovelace
GPU Name
GA102
AD104
Generation
Mining GPUs
Workstation Ada
(x000A)
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
Dual-slot
Length
285 mm
11.2 inches
168 mm
6.6 inches
Height
112 mm
4.4 inches
69 mm
2.7 inches
Outputs
No outputs
4x mini-DisplayPort 1.4a
Bus Interface
PCIe 1.0 x4
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
—
Workstation Ampere
Successor
—
Blackwell PRO W