NVIDIA GeForce GTX 660M Mac Edition vs NVIDIA GeForce RTX 4070 Max-Q
We compared two Mobile platform GPUs: 512MB VRAM GeForce GTX 660M Mac Edition and 8GB VRAM GeForce RTX 4070 Max Q to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 Max-Q 's Advantages
Released 9 years and 9 months late
Boost Clock1230MHz
More VRAM (8GB vs 512GB)
Larger VRAM bandwidth (256.0GB/s vs 80.00GB/s)
4224 additional rendering cores
Lower TDP (35W vs 50W)
Score
Benchmark
FP32 (float)
GeForce GTX 660M Mac Edition
0.73 TFLOPS
GeForce RTX 4070 Max Q
+1453%
11.34 TFLOPS
Graphics Card
Apr 2013
Release Date
Jan 2023
GeForce 600M
Generation
GeForce 40 Mobile
Mobile
Type
Mobile
MXM-B (3.0)
Bus Interface
PCIe 4.0 x8
Clock Speeds
-
Base Clock
735 MHz
-
Boost Clock
1230 MHz
1250 MHz
Memory Clock
2000 MHz
Memory
512MB
Memory Size
8GB
GDDR5
Memory Type
GDDR6
128bit
Memory Bus
128bit
80.00GB/s
Bandwidth
256.0GB/s
Render Config
-
-
-
-
SM Count
36
384
Shading Units
4608
32
TMUs
144
16
ROPs
48
-
Tensor Cores
144
-
RT Cores
36
16 KB (per SMX)
L1 Cache
128 KB (per SM)
256 KB
L2 Cache
32 MB
-
-
-
Theoretical Performance
7.600 GPixel/s
Pixel Rate
59.04 GPixel/s
30.40 GTexel/s
Texture Rate
177.1 GTexel/s
-
FP16 (half)
11.34 TFLOPS
729.6 GFLOPS
FP32 (float)
11.34 TFLOPS
30.40 GFLOPS
FP64 (double)
177.1 GFLOPS
Board Design
50W
TDP
35W
-
-
-
No outputs
Outputs
Portable Device Dependent
None
Power Connectors
None
Graphics Processor
GK107
GPU Name
AD106
-
GPU Variant
GN21-X6
Kepler
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
28 nm
Process Size
5 nm
1.27 billion
Transistors
22.9 billion
118 mm²
Die Size
188 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
8.9
5.1
Shader Model
6.8
