NVIDIA GeForce RTX 4070 GDDR6 vs NVIDIA CMP 50HX
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 GDDR6 and 10GB VRAM CMP 50HX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 GDDR6 's Advantages
Released 3 years and 2 months late
Boost Clock has increased by 60% (2475MHz vs 1545MHz)
More VRAM (12GB vs 10GB)
2304 additional rendering cores
Lower TDP (200W vs 250W)
NVIDIA CMP 50HX 's Advantages
Larger VRAM bandwidth (560.0GB/s vs 480.0GB/s)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 GDDR6
+163%
29.15 TFLOPS
CMP 50HX
11.07 TFLOPS
Graphics Card
Aug 2024
Release Date
Jun 2021
GeForce 40
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
1920 MHz
Base Clock
1350 MHz
2475 MHz
Boost Clock
1545 MHz
2500 MHz
Memory Clock
1750 MHz
Memory
12GB
Memory Size
10GB
GDDR6
Memory Type
GDDR6
192bit
Memory Bus
320bit
480.0GB/s
Bandwidth
560.0GB/s
Render Config
-
-
-
46
SM Count
56
5888
Shading Units
3584
184
TMUs
192
64
ROPs
80
184
Tensor Cores
448
46
RT Cores
56
128 KB (per SM)
L1 Cache
64 KB (per SM)
36 MB
L2 Cache
5 MB
-
-
-
Theoretical Performance
158.4 GPixel/s
Pixel Rate
123.6 GPixel/s
455.4 GTexel/s
Texture Rate
296.6 GTexel/s
29.15 TFLOPS
FP16 (half)
22.15 TFLOPS
29.15 TFLOPS
FP32 (float)
11.07 TFLOPS
455.4 GFLOPS
FP64 (double)
346.1 GFLOPS
Board Design
200W
TDP
250W
550 W
Suggested PSU
600 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
AD104
GPU Name
TU102
AD104-2XX-A1
GPU Variant
TU102-100-A1
Ada Lovelace
Architecture
Turing
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
35.8 billion
Transistors
18.6 billion
294 mm²
Die Size
754 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.9
CUDA
7.5
6.8
Shader Model
6.8
