RTX 4000 Ada Generation vs GeForce RTX 3070 Mobile

Place in the ranking	124	28
Place by popularity	not in top-100	not in top-100
Power efficiency	7.37	11.46
Architecture	Ampere (2020−2024)	Ada Lovelace (2022−2024)
GPU code name	GA104	AD104
Market segment	Laptop	Desktop
Release date	12 January 2021 (3 years ago)	9 August 2023 (1 year ago)

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	5120	6144
Core clock speed	1110 MHz	1500 MHz
Boost clock speed	1560 MHz	2175 MHz
Number of transistors	17,400 million	35,800 million
Manufacturing process technology	8 nm	5 nm
Power consumption (TDP)	125 Watt	130 Watt
Texture fill rate	249.6	417.6
Floating-point processing power	15.97 TFLOPS	26.73 TFLOPS
ROPs	80	80
TMUs	160	192
Tensor Cores	160	192
Ray Tracing Cores	40	48

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Laptop size	large	no data
Interface	PCIe 4.0 x16	PCIe 4.0 x16
Length	no data	245 mm
Width	no data	1-slot
Supplementary power connectors	no data	1x 16-pin

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR6	GDDR6
Maximum RAM amount	8 GB	20 GB
Memory bus width	256 Bit	160 Bit
Memory clock speed	1750 MHz	2250 MHz
Memory bandwidth	448.0 GB/s	360.0 GB/s
Shared memory	-	-

Connectivity and outputs

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display Connectors

No outputs

4x mini-DisplayPort 1.4a

API compatibility

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 Ultimate (12_2)	12 Ultimate (12_2)
Shader Model	6.5	6.7
OpenGL	4.6	4.6
OpenCL	2.0	3.0
Vulkan	1.2	1.3
CUDA	8.6	8.9

Synthetic benchmark performance

Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.

Combined synthetic benchmark score

This is our combined benchmark score. We are regularly improving our combining algorithms, but if you find some perceived inconsistencies, feel free to speak up in comments section, we usually fix problems quickly.

RTX 3070 Mobile 37.24

RTX 4000 Ada Generation 65.40
+75.6%

Passmark

This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.

RTX 3070 Mobile 14364

RTX 4000 Ada Generation 25225
+75.6%

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Average FPS across all PC games

Here are the average frames per second in a large set of popular games across different resolutions:

Full HD	116 −72.4%	200−210 +72.4%
1440p	76 −71.1%	130−140 +71.1%
4K	48 −66.7%	80−85 +66.7%

FPS performance in popular games

Full HD
Low Preset

Cyberpunk 2077

119

−68.1%

200−210
+68.1%

Full HD
Medium Preset

Assassin's Creed Odyssey	75−80 −64.6%	130−140 +64.6%
Assassin's Creed Valhalla	91 −64.8%	150−160 +64.8%
Battlefield 5	120−130 −75%	210−220 +75%
Call of Duty: Modern Warfare	75−80 −71.1%	130−140 +71.1%
Cyberpunk 2077	107 −68.2%	180−190 +68.2%
Far Cry 5	80−85 −72.8%	140−150 +72.8%
Far Cry New Dawn	90−95 −72%	160−170 +72%
Forza Horizon 4	180−190 −61.3%	300−310 +61.3%
Hitman 3	114 −75.4%	200−210 +75.4%
Horizon Zero Dawn	150−160 −72%	270−280 +72%
Metro Exodus	120−130 −73.6%	210−220 +73.6%
Red Dead Redemption 2	85−90 −70.5%	150−160 +70.5%
Shadow of the Tomb Raider	130−140 −70.4%	230−240 +70.4%
Watch Dogs: Legion	120−130 −74.6%	220−230 +74.6%

Full HD
High Preset

Assassin's Creed Odyssey	188 −59.6%	300−310 +59.6%
Assassin's Creed Valhalla	76 −71.1%	130−140 +71.1%
Battlefield 5	120−130 −75%	210−220 +75%
Call of Duty: Modern Warfare	75−80 −71.1%	130−140 +71.1%
Cyberpunk 2077	88 −70.5%	150−160 +70.5%
Far Cry 5	80−85 −72.8%	140−150 +72.8%
Far Cry New Dawn	90−95 −72%	160−170 +72%
Forza Horizon 4	180−190 −61.3%	300−310 +61.3%
Hitman 3	106 −69.8%	180−190 +69.8%
Horizon Zero Dawn	150−160 −72%	270−280 +72%
Metro Exodus	143 −74.8%	250−260 +74.8%
Red Dead Redemption 2	81 −72.8%	140−150 +72.8%
Shadow of the Tomb Raider	183 −63.9%	300−310 +63.9%
The Witcher 3: Wild Hunt	75−80 −68.8%	130−140 +68.8%
Watch Dogs: Legion	181 −65.7%	300−310 +65.7%

Full HD
Ultra Preset

Assassin's Creed Odyssey	75−80 −64.6%	130−140 +64.6%
Assassin's Creed Valhalla	68 −61.8%	110−120 +61.8%
Call of Duty: Modern Warfare	75−80 −71.1%	130−140 +71.1%
Cyberpunk 2077	74 −62.2%	120−130 +62.2%
Far Cry 5	80−85 −72.8%	140−150 +72.8%
Forza Horizon 4	167 −73.7%	290−300 +73.7%
Hitman 3	98 −73.5%	170−180 +73.5%
Horizon Zero Dawn	132 −74.2%	230−240 +74.2%
Shadow of the Tomb Raider	168 −72.6%	290−300 +72.6%
The Witcher 3: Wild Hunt	94 −70.2%	160−170 +70.2%
Watch Dogs: Legion	60 −66.7%	100−105 +66.7%

Full HD
Epic Preset

Red Dead Redemption 2

82
−70.7%

140−150

+70.7%

1440p
High Preset

Battlefield 5	70−75 −69%	120−130 +69%
Far Cry New Dawn	55−60 −75.4%	100−105 +75.4%

1440p
Ultra Preset

Assassin's Creed Odyssey	40−45 −75%	70−75 +75%
Assassin's Creed Valhalla	53 −69.8%	90−95 +69.8%
Call of Duty: Modern Warfare	40−45 −70.5%	75−80 +70.5%
Cyberpunk 2077	47 −70.2%	80−85 +70.2%
Far Cry 5	40−45 −74.4%	75−80 +74.4%
Forza Horizon 4	210−220 −65.9%	350−400 +65.9%
Hitman 3	68 −61.8%	110−120 +61.8%
Horizon Zero Dawn	112 −69.6%	190−200 +69.6%
Metro Exodus	91 −64.8%	150−160 +64.8%
Shadow of the Tomb Raider	125 −68%	210−220 +68%
The Witcher 3: Wild Hunt	50−55 −69.8%	90−95 +69.8%
Watch Dogs: Legion	159 −69.8%	270−280 +69.8%

1440p
Epic Preset

Red Dead Redemption 2

73
−64.4%

120−130

+64.4%

4K
High Preset

Battlefield 5	35−40 −62.2%	60−65 +62.2%
Far Cry New Dawn	30−35 −61.3%	50−55 +61.3%
Hitman 3	38 −71.1%	65−70 +71.1%
Horizon Zero Dawn	119 −68.1%	200−210 +68.1%
Metro Exodus	71 −69%	120−130 +69%
The Witcher 3: Wild Hunt	64 −71.9%	110−120 +71.9%

4K
Ultra Preset

Assassin's Creed Odyssey	24−27 −60%	40−45 +60%
Assassin's Creed Valhalla	33 −66.7%	55−60 +66.7%
Call of Duty: Modern Warfare	21−24 −73.9%	40−45 +73.9%
Cyberpunk 2077	22 −59.1%	35−40 +59.1%
Far Cry 5	21−24 −59.1%	35−40 +59.1%
Forza Horizon 4	93 −72%	160−170 +72%
Shadow of the Tomb Raider	71 −69%	120−130 +69%
Watch Dogs: Legion	27 −66.7%	45−50 +66.7%

4K
Epic Preset

Red Dead Redemption 2

−70.5%

75−80
+70.5%

This is how RTX 3070 Mobile and RTX 4000 Ada Generation compete in popular games:

RTX 4000 Ada Generation is 72% faster in 1080p
RTX 4000 Ada Generation is 71% faster in 1440p
RTX 4000 Ada Generation is 67% faster in 4K

Pros & cons summary

Performance score	37.24	65.40
Recency	12 January 2021	9 August 2023
Maximum RAM amount	8 GB	20 GB
Chip lithography	8 nm	5 nm
Power consumption (TDP)	125 Watt	130 Watt

RTX 3070 Mobile has 4% lower power consumption.

RTX 4000 Ada Generation, on the other hand, has a 75.6% higher aggregate performance score, an age advantage of 2 years, a 150% higher maximum VRAM amount, and a 60% more advanced lithography process.

The RTX 4000 Ada Generation is our recommended choice as it beats the GeForce RTX 3070 Mobile in performance tests.

Be aware that GeForce RTX 3070 Mobile is a notebook card while RTX 4000 Ada Generation is a desktop one.

Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.