NVIDIA GeForce RTX 4070 GDDR6 vs AMD Radeon HD 6670
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 GDDR6 and 1024MB VRAM Radeon HD 6670 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 13 years and 4 months late
Boost Clock2475MHz
More VRAM (12GB vs 1024GB)
Larger VRAM bandwidth (480.0GB/s vs 64.00GB/s)
5408 additional rendering cores
AMD Radeon HD 6670 's Advantages
Lower TDP (66W vs 200W)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 GDDR6
+3695%
29.15 TFLOPS
Radeon HD 6670
0.768 TFLOPS
Graphics Card
Aug 2024
Release Date
Apr 2011
GeForce 40
Generation
Northern Islands
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1920 MHz
Base Clock
-
2475 MHz
Boost Clock
-
2500 MHz
Memory Clock
1000 MHz
Memory
12GB
Memory Size
1024MB
GDDR6
Memory Type
GDDR5
192bit
Memory Bus
128bit
480.0GB/s
Bandwidth
64.00GB/s
Render Config
-
Compute Units
6
46
SM Count
-
5888
Shading Units
480
184
TMUs
24
64
ROPs
8
184
Tensor Cores
-
46
RT Cores
-
128 KB (per SM)
L1 Cache
8 KB (per CU)
36 MB
L2 Cache
256 KB
-
-
-
Theoretical Performance
158.4 GPixel/s
Pixel Rate
6.400 GPixel/s
455.4 GTexel/s
Texture Rate
19.20 GTexel/s
29.15 TFLOPS
FP16 (half)
-
29.15 TFLOPS
FP32 (float)
768.0 GFLOPS
455.4 GFLOPS
FP64 (double)
-
Board Design
200W
TDP
66W
550 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 1.3a
1x VGA
1x 16-pin
Power Connectors
None
Graphics Processor
AD104
GPU Name
Turks
AD104-2XX-A1
GPU Variant
Turks XT
(215-0803000)
Ada Lovelace
Architecture
TeraScale 2
TSMC
Foundry
TSMC
5 nm
Process Size
40 nm
35.8 billion
Transistors
0.716 billion
294 mm²
Die Size
118 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
3.0
OpenCL
1.2
1.3
Vulkan
N/A
8.9
CUDA
-
6.8
Shader Model
5.0
