NVIDIA GeForce RTX 4070 Mobile vs NVIDIA GeForce RTX 3070 Max-Q

Comparative analysis of NVIDIA GeForce RTX 4070 Mobile and NVIDIA GeForce RTX 3070 Max-Q videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: PassMark - G2D Mark, PassMark - G3D Mark, Geekbench - OpenCL, 3DMark Fire Strike - Graphics Score, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

NVIDIA GeForce RTX 4070 Mobile

NVIDIA GeForce RTX 3070 Max-Q

Differences

Reasons to consider the NVIDIA GeForce RTX 4070 Mobile

Videocard is newer: launch date 4 year(s) 1 month(s) later
Around 79% higher core clock speed: 1395 MHz vs 780 MHz
Around 31% higher boost clock speed: 1695 MHz vs 1290 MHz
Around 18% higher texture fill rate: 244.1 GTexel/s vs 206.4 GTexel/s
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 4 nm vs 8 nm
Around 33% higher memory clock speed: 2000 MHz, 16 Gbps effective vs 1500 MHz, 12 Gbps effective
Around 18% better performance in PassMark - G2D Mark: 758 vs 645
Around 27% better performance in PassMark - G3D Mark: 19562 vs 15398
Around 18% better performance in Geekbench - OpenCL: 109023 vs 92447
Around 13% better performance in 3DMark Fire Strike - Graphics Score: 2701 vs 2380
Around 20% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 218.946 vs 181.818
Around 12% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 1585.54 vs 1410.887

Specifications (specs)
Launch date	2023 vs 12 Jan 2021
Core clock speed	1395 MHz vs 780 MHz
Boost clock speed	1695 MHz vs 1290 MHz
Texture fill rate	244.1 GTexel/s vs 206.4 GTexel/s
Manufacturing process technology	4 nm vs 8 nm
Memory clock speed	2000 MHz, 16 Gbps effective vs 1500 MHz, 12 Gbps effective
Benchmarks
PassMark - G2D Mark	758 vs 645
PassMark - G3D Mark	19562 vs 15398
Geekbench - OpenCL	109023 vs 92447
3DMark Fire Strike - Graphics Score	2701 vs 2380
CompuBench 1.5 Desktop - Video Composition (Frames/s)	218.946 vs 181.818
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	1585.54 vs 1410.887

Reasons to consider the NVIDIA GeForce RTX 3070 Max-Q

Around 11% higher pipelines: 5120 vs 4608
Around 44% lower typical power consumption: 80 Watt vs 115 Watt
Around 41% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 449.647 vs 319.688

Specifications (specs)
Pipelines	5120 vs 4608
Thermal Design Power (TDP)	80 Watt vs 115 Watt
Benchmarks
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	449.647 vs 319.688
CompuBench 1.5 Desktop - T-Rex (Frames/s)	36.308 vs 36.174

Compare benchmarks

GPU 1: NVIDIA GeForce RTX 4070 Mobile
GPU 2: NVIDIA GeForce RTX 3070 Max-Q

PassMark - G2D Mark

GPU 1

GPU 2

758

645

PassMark - G3D Mark

GPU 1

GPU 2

19562

15398

Geekbench - OpenCL

GPU 1

GPU 2

109023

92447

3DMark Fire Strike - Graphics Score

GPU 1

GPU 2

2701

2380

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

319.688

449.647

CompuBench 1.5 Desktop - T-Rex (Frames/s)

GPU 1

GPU 2

36.174

36.308

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

218.946

181.818

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

1585.54

1410.887

Name	NVIDIA GeForce RTX 4070 Mobile	NVIDIA GeForce RTX 3070 Max-Q
PassMark - G2D Mark	758	645
PassMark - G3D Mark	19562	15398
Geekbench - OpenCL	109023	92447
3DMark Fire Strike - Graphics Score	2701	2380
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	319.688	449.647
CompuBench 1.5 Desktop - T-Rex (Frames/s)	36.174	36.308
CompuBench 1.5 Desktop - Video Composition (Frames/s)	218.946	181.818
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	1585.54	1410.887
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		4619.617
GFXBench 4.0 - Car Chase Offscreen (Frames)		24877
GFXBench 4.0 - Manhattan (Frames)		11471
GFXBench 4.0 - T-Rex (Frames)		13334
GFXBench 4.0 - Car Chase Offscreen (Fps)		24877
GFXBench 4.0 - Manhattan (Fps)		11471
GFXBench 4.0 - T-Rex (Fps)		13334

Compare specifications (specs)

	NVIDIA GeForce RTX 4070 Mobile	NVIDIA GeForce RTX 3070 Max-Q
Essentials
Architecture	Ada Lovelace	Ampere
Code name	AD106	GA104
Launch date	2023	12 Jan 2021
Place in performance rating	80	84
Type		Laptop
Technical info
Boost clock speed	1695 MHz	1290 MHz
Core clock speed	1395 MHz	780 MHz
Manufacturing process technology	4 nm	8 nm
Peak Double Precision (FP64) Performance	244.1 GFLOPS (1:64)	206.4 GFLOPS (1:64)
Peak Half Precision (FP16) Performance	15.62 TFLOPS (1:1)	13.21 TFLOPS (1:1)
Peak Single Precision (FP32) Performance	15.62 TFLOPS	13.21 TFLOPS
Pipelines	4608	5120
Pixel fill rate	81.36 GPixel/s	103.2 GPixel/s
Texture fill rate	244.1 GTexel/s	206.4 GTexel/s
Thermal Design Power (TDP)	115 Watt	80 Watt
Transistor count		17400 million
Video outputs and ports
Display Connectors	Portable Device Dependent	Portable Device Dependent
DisplayPort support
G-SYNC support
HDMI
Compatibility, dimensions and requirements
Form factor	IGP
Interface	PCIe 4.0 x16	PCIe 4.0 x16
Supplementary power connectors	None	None
Laptop size		large
API support
DirectX	12 Ultimate (12_2)	12 Ultimate (12_2)
OpenCL	3.0	3.0
OpenGL	4.6	4.6
Shader Model	6.7	6.7
Vulkan
Memory
Maximum RAM amount	8 GB	8 GB
Memory bandwidth	256.0 GB/s	384.0 GB/s
Memory bus width	128 bit	256 bit
Memory clock speed	2000 MHz, 16 Gbps effective	1500 MHz, 12 Gbps effective
Memory type	GDDR6	GDDR6
Technologies
GPU Boost
VR Ready