News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip
Illustration of the Apple A14 Bionic system-on-a-chip. Inspiration found here: https://www.techinsights.com/blog/two-new-apple-socs-two-market-events-apple-a14-and-m1

Apple A14 Bionic

Apple's 5 nm phone and tablet chip with six CPU cores and a 16-core Neural Engine

Photo: Henriok, CC0, via Wikimedia Commons

A mobile system on a chip built by Apple around six CPU cores, a four-core graphics unit and dedicated machine learning hardware. TSMC produced it from September 2020 until March 2025, and it was the first product to reach the market on a 5 nm process.

Share on WhatsApp

  • First commercial product built on a 5 nm process node
  • 11.8 billion transistors, up 38.8% from the A13
  • 16-core Neural Engine rated at 11 trillion operations per second
  • Die area of 88 mm2 with 134 million transistors per mm2
  • Produced from September 2020 until March 2025

What it is

This is a system on a chip, meaning a single piece of silicon that carries the processor, graphics, machine learning units and other blocks that a mobile device needs. Apple designed it for phones and tablets and TSMC built it. Production ran from 15 September 2020 to 4 March 2025. It carries the internal code APL1W01 and belongs to the Apple A series. Apple quoted gains of up to 40% for the CPU and up to 30% for the GPU against the older A12. A 16-core Neural Engine and fresh matrix accelerators handle machine learning work.

How it came about

Apple built the chip as the next step in its own silicon line, following the A13 Bionic. It reached buyers first inside the iPhone 12 family and the fourth-generation iPad Air. TSMC's first 5 nm line carried the design, which made this the earliest commercial product on that process. The chip stayed in production until 4 March 2025, when the tenth-generation iPad that used it was withdrawn.

Inside the chip

The CPU holds six cores split into two groups: two fast ones named Firestorm and four frugal ones named Icestorm, a pairing often called big.LITTLE. They speak the ARMv8.4-A instruction set. Each fast core has 8 MB of shared L2 cache behind it, the slow group 4 MB, and a 16 MB pool sits further out as system cache. Graphics come from an Apple four-core GPU. Machine learning runs on a 16-core Neural Engine rated at 11 trillion operations each second, plus second-generation matrix scalar multiplication blocks inside the CPU that Apple names AMX. An image processor supports computational photography, and video encode covers HEVC and H.264 while decode adds MPEG-4 Part 2 and Motion JPEG.

How it was made

TSMC fabricated the design on its N5 process, a first-generation 5 nm node. The die measures 88 mm2 and packs 134 million transistors per mm2, holding 11.8 billion in total. That is a 38.8% rise over the 8.5 billion of the A13. Chips ship in a package on package arrangement, stacked with LPDDR4X memory: 4 GB in the iPhone 12 and 6 GB in the iPhone 12 Pro.

Apple A14 Bionic
A drawing made by EveryChip from what this page says. It is a diagram, not a picture of the real chip.

Where it went

Four product families carried the chip. In Apple's phone line it powered the iPhone 12 Mini, iPhone 12, iPhone 12 Pro and iPhone 12 Pro Max. Tablets using it were the fourth-generation iPad Air and the tenth-generation iPad. The same core design later became the foundation of the M1 family used across Macintosh computers and iPads.

Versions and family

The A14 sits between the A13 Bionic before it and several successors. Apple moved iPhone models to the A15 Bionic and iPad models to the A16 Bionic, while the iPad Air shifted to the M1. The M1 itself is treated as a variant of this design. Other chips sharing the Firestorm and Icestorm cores form a wider group of related parts.

Why it matters

Being first to market on a 5 nm node gave the industry an early look at what that process could deliver. The transistor total climbed sharply from the previous generation while the package stayed compact enough for phones. Its cores and machine learning blocks went on to underpin the M1 series, so the design reached laptop and desktop computers as well as handhelds.

Questions people ask about Apple A14 Bionic

What kind of chip is the A14 Bionic?

It is a system on a chip for mobile devices. One piece of silicon carries the CPU, graphics processor, machine learning units and image processor, so a phone or tablet needs few other main chips.

Who designed and who built it?

Apple Inc. designed the chip in the United States. TSMC manufactured it in Taiwan on the company's N5 process, a first-generation 5 nm node.

How is the processor arranged?

Six CPU cores split into two fast Firestorm cores and four efficient Icestorm cores. They implement ARMv8.4-A. An Apple four-core GPU handles graphics, and a 16-core Neural Engine plus AMX matrix blocks handle machine learning.

Which devices used it?

Apple put it in the iPhone 12 Mini, iPhone 12, iPhone 12 Pro and iPhone 12 Pro Max, along with the fourth-generation iPad Air and the tenth-generation iPad.

What came after it?

iPhone models moved to the A15 Bionic and iPad models to the A16 Bionic, while the iPad Air adopted the M1. The M1 itself grew out of this design.

Good reading and sources

Where this page comes from

The facts on this page come from the Wikipedia article "Apple A14", written by its contributors and used under the CC BY-SA 4.0 licence, and from its Wikidata record (CC0). EveryChip rewrote the text in its own words, with AI assistance, and compares every page with the article to make sure no passage is copied. It may be reused under the same CC BY-SA 4.0 licence with a link back.

It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.