Zotac GeForce RTX 4070 AMP Airo is the company's top-of-the-line custom design based on the RTX 4070 Ada. It gives you the company's highest factory overclock for this GPU, its most elaborate VRM solution, and is among the handful of custom RTX 4070 cards to come with a 12VHPWR connector. The AMP Airo is also the company's most premium-looking RTX 4070 product, and is sure to look like it's from a segment above, with eye-catching RGB LED lighting and a large triple-slot design. The GeForce RTX 4070 is designed to offer maxed out gaming with ray tracing at 1440p resolution, as well as high refresh-rate e-sports gaming. It's also capable of 4K Ultra HD, if you dial down your game's settings, or let GeForce Experience to choose the best ones. You can also take advantage of DLSS and DLAA, as well as the latest DLSS 3 Frame Generation.
The GeForce RTX 4070 Ada is based on the same 5 nm AD104 silicon as the RTX 4070 Ti, but is slightly cut down. The card comes with 46 out of 60 streaming multiprocessors (SM) enabled, which results in 5,888 CUDA cores, 46 RT cores, 184 Tensor cores, and 184 TMUs. The GPU's ROP count has been reduced to 64 from 80 on the RTX 4070 Ti, as has the on-die L2 cache, to 36 MB from 48 MB on the Ti. Interestingly, the shader count is identical to that of the popular RTX 3070, which it succeeds. The memory sub-system, interestingly, is unchanged from the RTX 4070 Ti—you get 12 GB of 21 Gbps GDDR6X memory across a 192-bit memory interface. Generationally, the memory bus width is narrower, but the memory size and speed have both been increased by over 50%. NVIDIA has re-architected the memory sub-system, with large on-die caches playing a big role in reducing the round-trips to the video memory, allowing NVIDIA to narrow the bus width. The biggest difference between the RTX 4070 and the RTX 4070 Ti is the 30% lower typical power of just 200 W, which has enabled board partners to opt for a single 8-pin PCIe power connector. The Zotac AMP Airo, however, uses the more advanced 16-pin 12VHPWR.
The new GeForce Ada Lovelace graphics architecture debuts the third generation of RTX, the pioneering gaming graphics innovation by NVIDIA that combines real-time ray traced elements with conventional raster graphics, to significantly increase realism. Even this bit of ray tracing requires an enormous amount of compute power, and so the company innovated fixed-function hardware in the form of RT cores, and uses AI deep-learning for de-noising—which is where the Tensor cores step in. The new Ada Lovelace CUDA core, in addition to generational improvements in IPC and math formats, supports shader execution reordering. The 3rd Gen RT core, in addition to generational ray intersection performance improvements, introduces new features such as Displaced Micro-meshes. DLSS 3 is perhaps the biggest innovation with the RTX 40-series. Entire alternate frames are generated entirely using AI, without involving the graphics rendering pipeline, nearly doubling performance, all thanks to the new optical flow accelerator.
The Zotac GeForce RTX 4070 AMP Airo features the same Ice Storm 2.0 triple-slot, triple-fan cooling solution that the company uses with its RTX 4070 Ti AMP series graphics cards. The cooler is designed for 300 W-class GPUs from a segment above. A large aluminium fin-stack heatsink is ventilated by three large fans with a high degree of airflow optimization and fan tuning. The 30.7 cm card is longer than the PCB underneath, so much of the airflow from the third fan passes through the cooler, and out vents on the backplate. The RTX 4070 AMP Airo features Zotac's Spectra 2.0 RGB lighting, in the form of a large RGB LED diffuser along the top of the card that resembles a neon sign. The Zotac AMP Airo comes with factory overclocked speeds of up to 2535 MHz boost compared to 2475 MHz reference, while leaving the memory speed untouched at 21 Gbps. While the default power limit sticks to NVIDIA reference settings of 200 W, the manual adjustment range goes up to 240 W. Zotac is pricing the RTX 4070 AMP Airo at $640, a not-unreasonable $40 premium over the NVIDIA MSRP.
GeForce RTX 4070 Market Segment Analysis
Price
Cores
ROPs
Core Clock
Boost Clock
Memory Clock
GPU
Transistors
Memory
Arc A770
$290
4096
128
2100 MHz
N/A
2187 MHz
ACM-G10
21700M
16 GB, GDDR6, 256-bit
RTX 2080
$310
2944
64
1515 MHz
1710 MHz
1750 MHz
TU104
13600M
8 GB, GDDR6, 256-bit
RTX 3060 Ti
$320
4864
80
1410 MHz
1665 MHz
1750 MHz
GA104
17400M
8 GB, GDDR6, 256-bit
RX 6700 XT
$320
2560
64
2424 MHz
2581 MHz
2000 MHz
Navi 22
17200M
12 GB, GDDR6, 192-bit
RTX 2080 Ti
$420
4352
88
1350 MHz
1545 MHz
1750 MHz
TU102
18600M
11 GB, GDDR6, 352-bit
RTX 3070
$400
5888
96
1500 MHz
1725 MHz
1750 MHz
GA104
17400M
8 GB, GDDR6, 256-bit
RTX 3070 Ti
$500
6144
96
1575 MHz
1770 MHz
1188 MHz
GA104
17400M
8 GB, GDDR6X, 256-bit
RX 6800
$450
3840
96
1815 MHz
2105 MHz
2000 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RX 6800 XT
$510
4608
128
2015 MHz
2250 MHz
2000 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RTX 3080
$550
8704
96
1440 MHz
1710 MHz
1188 MHz
GA102
28000M
10 GB, GDDR6X, 320-bit
RTX 4070
$600
5888
64
1920 MHz
2475 MHz
1313 MHz
AD104
35800M
12 GB, GDDR6X, 192-bit
Zotac RTX 4070 AMP Airo
$640
5888
64
1920 MHz
2535 MHz
1313 MHz
AD104
35800M
12 GB, GDDR6X, 192-bit
RTX 3080 Ti
$750
10240
112
1365 MHz
1665 MHz
1188 MHz
GA102
28000M
12 GB, GDDR6X, 384-bit
RX 6900 XT
$620
5120
128
2015 MHz
2250 MHz
2000 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RX 6950 XT
$680
5120
128
2100 MHz
2310 MHz
2250 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RTX 3090
$800
10496
112
1395 MHz
1695 MHz
1219 MHz
GA102
28000M
24 GB, GDDR6X, 384-bit
RTX 4070 Ti
$800
7680
80
2310 MHz
2610 MHz
1313 MHz
AD104
35800M
12 GB, GDDR6X, 192-bit
RX 7900 XT
$800
5376
192
2000 MHz
2400 MHz
2500 MHz
Navi 31
57700M
20 GB, GDDR6, 320-bit
RTX 3090 Ti
$1000
10752
112
1560 MHz
1950 MHz
1313 MHz
GA102
28000M
24 GB, GDDR6X, 384-bit
RTX 4080
$1150
9728
112
2205 MHz
2505 MHz
1400 MHz
AD103
45900M
16 GB, GDDR6X, 256-bit
RX 7900 XTX
$960
6144
192
2300 MHz
2500 MHz
2500 MHz
Navi 31
57700M
24 GB, GDDR6, 384-bit
RTX 4090
$1600
16384
176
2235 MHz
2520 MHz
1313 MHz
AD102
76300M
24 GB, GDDR6X, 384-bit
Packaging
The Card
Zotac is taking an all-smooth approach with their GeForce RTX 4070 AMP Airo. The curves on their card are almost female-elegant. On the back you get a high-quality metal backplate, the front cooler shroud is made from plastic.
Zotac has integrated a large RGB lighting element along the top edge. The lighting extends to the back of the card, where it adds a little bit of bling on this side of the cooler.
Dimensions of the card are 31.0 x 12.5 cm, and it weighs 1138 g.
Installation requires three slots in your system. The card's width is 57 mm.
Display connectivity includes three standard DisplayPort 1.4a ports and one HDMI 2.1a (same as Ampere).
The new 8th Gen NVENC now accelerates AV1 encoding, besides HEVC. You also get an "optical flow accelerator" unit that is able to calculate intermediate frames for videos, to smooth playback. The same hardware unit is used for frame generation in DLSS 3.
The card uses the new 12+4 pin ATX 12VHPWR connector, which is rated for up to 600 W of power draw. An adapter cable from 2x PCIe 8-pin is included (which is rated for up to 300 W). The card's default power limit is 200 W. Of course the 3x and 4x 8-pin to 16-pin adapter cables from other Ampere cards will work with the RTX 4070, but the card won't need or use that much power.
Teardown
The thermal solution on the Zotac AMP Airo uses six heatpipes. The main heatsink also provides cooling for the memory chips and VRM circuitry.
The backplate is made of metal and protects the card against damage during installation and handling.
High-resolution PCB Pictures
These pictures are for the convenience of volt modders and people who would like to see all the finer details on the PCB. Feel free to link back to us and use these in your articles, videos or forum posts.
High-resolution versions are also available (front, back).
Circuit Board (PCB) Analysis
GPU voltage is a nine-phase design, managed by a uPI uP9512R controller.
Alpha & Omega AOZ5311NQI BLN3 DrMOS components are used for GPU voltage; they are rated for 55 A of current each.
Memory voltage is a two-phase design, managed by a uPI uP9529Q controller.
For memory, Alpha & Omega AOZ5311NQI BLN30 are used, too, with a 55 A rating.
The GDDR6X memory chips are made by Micron and carry the model number D8BZC, which decodes to MT61K512M32KPA-21:U. They are specified to run at 1313 MHz (21 Gbps GDDR6 effective).
NVIDIA's AD104 graphics processor is the company's third Ada Lovelace GPU. It is built using a 5 nanometer process at TSMC Taiwan, with a transistor count of 35.8 billion and a die size of 295 mm².
Test System
Test System - GPU 2023.2
Processor:
Intel Core i9-13900K Raptor Lake, 5.8 GHz, 8+16 cores / 32 threads PL1 = PL2 = 320 W
Benchmark scores in other reviews are only comparable when this exact same configuration is used.
All games and cards are tested with the drivers listed above—no performance results were recycled between test systems. Only this exact system with exactly the same configuration is used for all results in this review.
All graphics cards are tested using the same game version.
All games are set to their highest quality setting unless indicated otherwise.
AA and AF are applied via in-game settings, not via the driver's control panel.
Before starting measurements, we heat up the card for each test to ensure a steady state is tested. This ensures that the card won't boost to unrealistically high clocks for only a few seconds until it heats up, as that doesn't represent prolonged gameplay.
For better real-life applicability, all game tests use custom in-game test scenes, not the integrated benchmarks
All cards used for comparison are reference designs. When a reference design does not exist, we go the extra mile and buy the closest possible match, using reference clocks and default power limit.
Each game is tested at these screen resolutions:
1920x1080: Most popular monitor resolution.
2560x1440: Intermediary resolution between Full HD and 4K, with reasonable performance requirements.
3840x2160: 4K Ultra HD resolution, available on high-end monitors.