Fact-checked by Grok 2 weeks ago

Apple M2

The Apple M2 is a system on a chip (SoC) developed by Apple Inc. as the second-generation processor in its Apple silicon family, succeeding the M1 and powering select Mac and iPad devices with enhanced performance and efficiency. Announced on June 6, 2022, it is built on TSMC's second-generation 5-nanometer manufacturing process and incorporates 20 billion transistors, representing a 25% increase over the M1's transistor count. The M2 features an 8-core CPU design with four high-performance cores and four high-efficiency cores, delivering up to 18% faster single-core and multi-core performance compared to the . Its integrated GPU is configurable with 8 or 10 cores, providing up to 35% greater graphics performance than the M1's GPU while maintaining power efficiency. The chip also includes a 16-core Neural Engine capable of executing 15.8 trillion operations per second, a 40% improvement over the M1's Neural Engine for tasks. Additionally, it supports up to 24 GB of unified memory with 100 GB/s of —50% higher than the M1—and includes hardware-accelerated media engines for ProRes encoding and decoding, as well as 8K video support. The M2 debuted in the redesigned and updated 13-inch in 2022, both offering configurations with the base 8-core GPU or optional 10-core variant. It was later integrated into the 11-inch (4th generation) and 12.9-inch (6th generation) models announced on October 18, 2022. In 2023, the M2 powered the desktop computer and the 15-inch laptop, expanding its use across Apple's portable and compact systems. In 2024, the M2 powered the sixth-generation in 11-inch and 13-inch models.

History and Development

Announcement and Release Timeline

The Apple M2 chip was first unveiled by Apple on June 6, 2022, during the company's (WWDC), marking the introduction of the second-generation for computers. This announcement highlighted the M2 as a successor to the , driven by the need for enhanced performance and efficiency to support evolving user workflows. The base M2 made its debut in consumer products shortly thereafter, integrating into the redesigned 13-inch , which became available for order on July 8, 2022, and shipped starting July 15, 2022, as well as the updated 13-inch , available for order on June 17, 2022, and released on June 24, 2022. Subsequent variants expanded the M2 family in early 2023. On January 17, 2023, Apple announced the M2 Pro and M2 Max chips, which were integrated into the refreshed 14-inch and 16-inch models as well as the with base M2 and M2 Pro, all available for order the same day and in stores starting January 24, 2023. The M2 Ultra variant followed on June 5, 2023, at WWDC, powering the updated and the new , both available for order immediately and shipping from June 13, 2023. The base M2 continued to expand with the 15-inch announced on June 5, 2023, and available starting June 13, 2023. Beyond Macs, the M2 found applications in other Apple devices. The sixth-generation iPad Pro models—featuring 11-inch and 12.9-inch displays—were announced on October 18, 2022, and released on October 26, 2022. Later, the sixth-generation iPad Air, available in 11-inch and 13-inch sizes, incorporated the base M2 and was announced on May 7, 2024, with availability starting May 15, 2024; it was succeeded by a seventh-generation model with M3 chip announced on March 4, 2025. Additionally, Apple Vision Pro, a spatial computing headset powered by the M2 alongside a dedicated R1 chip, was announced on June 5, 2023, and launched in the United States on February 2, 2024; it received an upgrade to M5 chip announced on October 15, 2025. As of November 2025, the M2 series continued a gradual transition toward successors, with the family introduced in October 2023, the in May 2024 (including in the updated October 2024), the in Air (March 2025), and the in Vision Pro (October 2025).

Design Goals and Improvements over

The Apple series was engineered with primary objectives to elevate computational efficiency and performance within the constraints of and compact form factors, building iteratively on the 's foundation of unified and low power consumption. Key targets included enhancing single- and multi-threaded CPU performance by up to 18%, enabling faster execution of intensive tasks like code compilation and while using significantly less power—matching the peak output of comparable PC chips at one-fourth the energy draw. This focus on balanced scaling allowed the to support emerging professional demands without compromising the portability that defined Apple's silicon transition. Graphics capabilities saw targeted advancements, with the GPU delivering up to 35% faster performance over the , prioritizing improvements in rendering and visual effects for creative applications such as and . Complementing this, the upgraded media engine introduced higher-bandwidth for ProRes encoding and decoding, facilitating seamless handling of multiple or 8K streams directly on the system-on-chip to expedite workflows in and . Power efficiency remained a cornerstone goal, optimized to enable thinner device designs like the , which reduced overall volume by 20% while sustaining all-day battery life under heavy loads. To address pro-level needs, the M2 lineup expanded into , , and variants with scaled-up core configurations, providing greater parallelism for demanding scenarios in , scientific simulation, and large-scale . These higher-end models support up to 192 GB of unified , a substantial increase that accommodates memory-intensive operations without external dependencies. The 16-core Neural Engine, upgraded to 15.8 trillion operations per second (), achieves approximately 40% faster inference than the M1's 11 , enhancing capabilities in AI-driven features like real-time photo enhancement and processing.

Architecture

Central Processing Unit (CPU)

The Apple M2 series central processing unit (CPU) is built on the ARMv8.6-A instruction set architecture, featuring a hybrid design that balances high-performance and energy-efficient cores to optimize both computational throughput and power consumption. In the base M2 configuration, the CPU consists of four high-performance Avalanche cores clocked up to 3.5 GHz and four efficiency-oriented Blizzard cores operating up to 2.4 GHz, enabling the chip to handle demanding workloads while maintaining efficiency for lighter tasks. These cores employ advanced superscalar out-of-order execution pipelines, allowing instructions to be dynamically reordered for improved instruction-level parallelism, alongside sophisticated branch prediction mechanisms that anticipate control flow to minimize pipeline stalls. Additionally, the CPU supports 128-bit SIMD instructions through the NEON unit for vector processing, complemented by the integrated Apple Matrix Coprocessor (AMX) for accelerated matrix multiplication operations, which is particularly useful for machine learning and scientific computing tasks. The CPU's core scaling across M2 variants enhances multi-threaded performance for professional workflows. The M2 Pro offers configurations with either six performance cores and four efficiency cores or eight performance cores and four efficiency cores, providing up to 40% more CPU core count than the base M2 for better parallelism in creative and development applications. The M2 Max maintains the eight performance and four efficiency core layout but supports higher sustained clock speeds and power envelopes due to its larger package, enabling superior single- and multi-threaded performance in sustained loads. The top-tier M2 Ultra achieves 24 cores total—16 performance and eight efficiency—by linking two M2 Max dies via Apple's UltraFusion interconnect, effectively doubling the core count while preserving low-latency inter-die communication for seamless operation as a single logical CPU. A multi-level supports the CPU's and speed. Each performance core features a private 192 L1 instruction and 128 L1 , while each core has a 128 L1 instruction and 64 L1 , ensuring low-latency access to frequently used . The four performance cores share a 16 MB , and the four cores share a 4 MB , with these mid-level caches buffering from main memory to reduce access times. Across variants, a shared system-level (SLC) provides additional buffering: 8 MB in the base , expanding to 24 MB in the , 48 MB in the Max, and 96 MB in the Ultra, all accessible by CPU, GPU, and other accelerators for unified memory .

Graphics Processing Unit (GPU)

The Apple M2 (GPU) integrates up to 10 cores in its base configuration, delivering peak single-precision floating-point (FP32) performance of 3.6 teraflops. This design builds on Apple's custom , utilizing a tile-based deferred rendering (TBDR) that processes the in small tiles to minimize access and enhance efficiency for rendering and compute tasks. The GPU operates at a maximum clock speed of 1.4 GHz, with each core containing 128 ALUs for parallel execution of shaders and texture operations. The TBDR approach supports the Metal 3 graphics and compute , which enables developers to leverage compute shaders for non-graphics workloads such as simulations and inference on the GPU. Metal 3 also introduces variable rate shading, allowing finer control over shading rates across the screen to optimize in scenes without sacrificing visual . These features facilitate efficient handling of graphics-intensive applications, from real-time rendering to parallel compute operations. A dedicated media engine complements the GPU by providing for video codecs, including encode and decode support for H.264, HEVC, ProRes, and ProRes RAW. This enables seamless processing of professional video workflows, such as editing multiple 8K ProRes streams with low and power consumption. The engine's integration ensures that graphics and media tasks share resources effectively within the . The GPU scales across variants to address varying workloads, maintaining the TBDR pipeline and media engine while increasing core counts and . The Pro features 16 or 19 cores with up to 6.8 TFLOPS FP32 performance and 200 GB/s . The Max doubles this to 30 or 38 cores, achieving up to 13.6 TFLOPS and 400 GB/s for demanding creative applications. The top-tier Ultra combines two Max dies via the UltraFusion interconnect—a high-bandwidth silicon with over 2.5 TB/s throughput—resulting in 60 or 76 cores and up to 27.2 TFLOPS, enabling workstation-level graphics processing as a unified .
VariantGPU CoresPeak FP32 (TFLOPS)Memory Bandwidth (GB/s)
8–102.9–3.6100
M2 Pro16–195.8–6.8200
M2 Max30–3810.9–13.6400
M2 Ultra60–7621.8–27.2800
The unified memory architecture shared across CPU and GPU cores provides low-latency access for graphics data, reducing overhead in hybrid CPU-GPU workloads.

Neural Processing Unit (NPU)

The in the Apple M2 chip, known as the Neural Engine, is a dedicated accelerator designed to perform inference tasks efficiently on-device. It consists of 16 cores capable of delivering up to 15.8 trillion operations per second () at INT8 precision, marking a 40 percent improvement over the M1's Neural Engine. This performance enables rapid execution of operations, such as convolutions and multiplications, which are fundamental to workloads. The Neural Engine integrates seamlessly with Apple's Core ML framework, allowing developers to deploy optimized models for tasks like image recognition, , and real-time audio analysis directly on the device without relying on cloud processing. Architecturally, the Neural Engine employs a design optimized for high-throughput multiplications, a core operation in models. This structure facilitates efficient data flow between processing elements, minimizing memory access overhead and maximizing compute utilization for . It supports sparsity in models through Core ML optimizations, where pruned neural networks can run with reduced and improved on the hardware. Additionally, while primarily focused on FP16 and INT8 precisions for , the M2 ecosystem enables bfloat16 usage in light training or hybrid workflows via integration with other accelerators, enhancing for certain tasks. The Neural Engine is tightly integrated with the image signal processor (ISP) to accelerate features, such as depth mapping, semantic segmentation, and in photos and videos captured by the device's cameras. This collaboration allows for advanced on-device processing, like object detection and portrait mode effects, without taxing the CPU or GPU. In video workflows, it contributes to enhanced playback and processing by supporting upscaling and quality improvements, leveraging its ML capabilities for tasks like frame interpolation. For non-optimized ML tasks that cannot fully utilize the Neural Engine, the system falls back to the CPU or GPU to ensure compatibility. Across M2 variants, the Neural Engine remains uniform with 16 cores and 15.8 performance in the base M2, M2 Pro, and M2 Max configurations. The M2 Ultra doubles this to 32 cores and 31.6 by combining two M2 Max dies. Higher in the Pro, Max, and Ultra variants—up to 400 GB/s compared to 100 GB/s in the base model—enables the Neural Engine to handle larger models and datasets more effectively, reducing bottlenecks in memory-intensive scenarios.

Memory and Interconnect

The Apple M2 series employs a unified , where the CPU, GPU, Neural Engine, and other components share a single high-bandwidth pool of memory integrated directly on the package. This design eliminates the need for data duplication across separate memory spaces, enabling efficient and reduced overhead in data-intensive workloads. The base M2 utilizes LPDDR5-6400 , available in configurations of 8 , 16 , or 24 , delivering up to 100 of . Higher-end variants scale this architecture for greater capacity and throughput. The M2 Pro supports 16 GB or 32 GB of LPDDR5-6400 memory with 200 GB/s bandwidth, doubling the base model's capabilities to handle more demanding multitasking and professional applications. The M2 Max extends this to 32 GB, 64 GB, or 96 GB at 400 GB/s bandwidth, while the M2 Ultra reaches 64 GB, 128 GB, or 192 GB with an impressive 800 GB/s bandwidth, facilitating seamless operation of large-scale computations across all SoC elements. Complementing the DRAM, the M2 incorporates on-package SRAM in the form of a system-level cache (SLC) for ultra-low-latency access to frequently used data. This SLC, shared among key components like the GPU, totals 8 MB in the base M2 and scales accordingly in Pro and Max variants. The underlying coherent interconnect fabric ensures cache consistency and high-speed data transfer, providing up to 2.5 times the bandwidth of the M1's equivalent interconnect—exceeding 1 TB/s in L2 cache access for models like the M2 Pro—thereby minimizing bottlenecks in real-time processing. Unlike traditional GPU designs with dedicated VRAM, the M2's unified eliminates separate pools, allowing all components to draw from the same resource without costly copies. This shared approach significantly lowers in graphics rendering and tasks, where rapid access to large datasets is critical; for instance, it supports hardware-accelerated ray tracing by enabling direct sharing between the CPU and GPU.

Manufacturing and Integration

Fabrication Process

The Apple M2 series is fabricated by Taiwan Semiconductor Manufacturing Company (TSMC) using its second-generation 5 nm process technology, designated as the N5P node. This enhanced process builds on the original N5 node employed for the M1 series, offering approximately 5% higher performance or 10% lower power consumption at iso-speed while maintaining comparable logic density. The N5P utilizes fin field-effect transistor (FinFET) architecture, enabling efficient scaling of complex system-on-chip designs with reduced manufacturing variability. The base M2 integrates 20 billion transistors on this process, a 25% increase over the M1's 16 billion, facilitated by refinements in the N5P that support greater integration without a proportional die area expansion. These optimizations contribute to overall stability, as the mature 5 nm family benefits from established techniques that minimize defects in high-volume runs. Subsequent variants in the series—M2 Pro, M2 Max, and M2 Ultra—likewise employ the second-generation , scaling transistor counts to 40 billion, 67 billion, and 134 billion, respectively, while leveraging Apple's custom blocks for efficient and reduced leakage in dense layouts. The M2 series did not transition to TSMC's 3 nm node, which was introduced later and reserved for the M3 generation to prioritize further density gains and efficiency advancements. This decision allowed Apple to capitalize on the proven yields and cost-effectiveness of the 5 nm for broader device deployment.

Chip Packaging and Scaling

The base M2 and M2 /Max chips employ a single-die System-in-Package () design, integrating the SoC die with and other components using Ball-Grid-Array (BGA) packaging technology. This configuration incorporates unified directly onto the package alongside the processor, supporting configurations up to 96 GB for the M2 Max, and includes integrated I/O capabilities such as Thunderbolt 4 and ports for high-speed connectivity. The approach enables a compact suitable for thin laptops and compact desktops, while maintaining efficient data transfer between the CPU, GPU, and subsystems. In contrast, the M2 Ultra utilizes Apple's proprietary UltraFusion packaging to scale performance by combining two M2 Max dies into a single cohesive unit. This technology employs a silicon interposer that links the dies with over 10,000 signals, delivering more than 2.5 TB/s of low-latency interprocessor to enable seamless operation as one . The result supports up to 24 CPU cores and 60 to 76 GPU cores, effectively doubling the capabilities of a single M2 Max while preserving unified across the package. Apple's M2 series leverages TSMC's Integrated Fan-Out (InFO) packaging technology, particularly the InFO-L variant for larger configurations like the M2 Ultra, to achieve high-density integration in compact form factors. InFO enables fan-out redistribution layers that connect the die to external interfaces without traditional substrates, facilitating stacked memory configurations up to 192 GB of unified LPDDR5 in the M2 Ultra for demanding workloads in professional desktops. This advanced packaging reduces overall package size and improves signal integrity, contributing to the chips' suitability for slim devices like the MacBook Air while supporting scalable multi-die designs. Thermal management in the M2 packaging has seen enhancements through the introduction of an integrated (IHS) on the DRAM packages, which improves heat dissipation from memory components during prolonged operation. This upgrade, observed in the M2 Pro compared to prior generations, allows for better uniformity across the SiP, enabling sustained performance boosts in both and configurations without excessive throttling under load.

Performance Characteristics

Computational Benchmarks

The Apple M2 series demonstrates strong computational performance across standardized benchmarks, with results varying by variant due to differences in core counts and . In CPU-focused tests like Geekbench 6, the base M2, featuring an 8-core CPU, achieves a single-core score of approximately 2,586 and a multi-core score of 9,670, reflecting efficient handling of both lightweight and parallel workloads. These scores position the base M2 as competitive with mid-range and processors from the same era in single-threaded tasks, while its multi-core results highlight improvements in thread scaling over prior generations. Higher-end variants scale performance notably in multi-threaded scenarios. The M2 Pro and M2 Max, both with 12-core CPUs, deliver multi-core 6 scores around 14,400 to 14,700, representing roughly 1.5 times the base model's capability in tasks like video encoding or . The M2 Ultra, combining two M2 Max dies for a 24-core CPU, pushes multi-core scores to approximately 21,388, offering up to 2.2 times the base M2's performance and enabling workstation-level productivity in multi-threaded applications.
VariantGeekbench 6 Single-CoreGeekbench 6 Multi-Core
Base M2~2,586~9,670
M2 Pro~2,656~14,438
M2 Max~2,749~14,731
M2 Ultra~2,776~21,388
For GPU performance, the series excels in compute-intensive tasks measured by theoretical throughput and API-specific benchmarks. The base M2's 10-core GPU provides 3.6 TFLOPS of peak floating-point performance, scaling linearly across variants to 6.8 TFLOPS for the M2 Pro (19 cores), 13.6 TFLOPS for the M2 Max (38 cores), and 27.2 TFLOPS for the M2 Ultra (up to 76 cores). In practical tests, the base M2 achieves a 6 Metal score of around 42,000, suitable for graphics rendering and acceleration on macOS. The M2 Ultra reaches over 220,000 in 6 Metal. In certain cross-platform compute benchmarks, the M2 Ultra outperforms discrete GPUs like the 4070 Ti while maintaining integrated efficiency. The Neural Processing Unit (NPU) further bolsters computational capabilities for tasks. Across all M2 variants, the 16-core Neural Engine delivers 15.8 , enabling up to 40% faster performance in Core ML models compared to the M1's 11 unit, particularly in inference workloads like image recognition and . This enhancement supports seamless on-device without relying on cloud resources.

Power Efficiency and Thermal Management

The Apple M2 chip emphasizes power efficiency through its second-generation 5 nm process, enabling low thermal design power (TDP) ratings suitable for compact, fanless devices. The base M2 operates at a TDP of approximately 15 W in standard configurations, such as the MacBook Air, while Pro variants can scale up to 30 W to support higher performance envelopes. Efficiency cores in the M2 architecture consume significantly less power than performance cores—estimated at around 50% lower draw per core—allowing the system to handle light workloads with minimal energy use while reserving higher power for intensive tasks. This design contributes to overall system power consumption as low as 4 W during idle or light activities. Compared to its predecessor, the M2 achieves up to 18% higher CPU and 35% better GPU at the same power envelope as the , according to Apple's engineering data. This enhanced per watt supports prolonged battery life and enables entirely fanless operation in devices like the , where the chip maintains cool surface temperatures even during graphics-intensive workloads. The architecture's focus on efficiency reduces the need for aggressive cooling, allowing systems to operate quietly without active fans under typical usage. Thermal management in the M2 relies on dynamic voltage and to prevent overheating. In fanless designs, this is mitigated by efficient heat spreading materials like sheets and vapor chambers integrated into device . For higher-end variants, the M2 Pro and Max maintain similar efficiency ratios despite increased core counts, while the M2 Ultra—formed by linking two M2 Max dies via UltraFusion interconnect—supports power draws up to 120 W yet preserves per-watt efficiency through shared resources and minimal interconnect overhead, enabling sustained operation in multi-core scenarios without proportional power spikes.

Chip Variants

Base M2

The base Apple M2 is a () featuring 20 billion transistors, fabricated on TSMC's second-generation . It includes an 8-core CPU with 4 high-performance cores and 4 high-efficiency cores, designed for balanced in everyday and professional tasks. The GPU configuration offers 8 or 10 cores, providing up to 35% faster graphics performance compared to the M1 at maximum power. Memory in the base M2 utilizes a unified with LPDDR5, configurable from 8 GB to 24 GB, and delivers 100 GB/s for efficient between CPU, GPU, and other components. This setup supports up to two external displays at resolutions up to 6K at 60 Hz, depending on the connected device. Primarily deployed in entry-level Apple devices like compact laptops and desktops, the base prioritizes power efficiency over maximum throughput. This single-die design forms the core for scaling to more advanced M2 family members, such as the and Max, through increased core counts and .

M2 Pro

The Apple M2 Pro is a mid-range () in the M2 family, designed to enhance performance for professional workflows in laptops and desktops while maintaining efficiency for mobile use. Built on a second-generation 5-nanometer process, it integrates 40 billion transistors on a single die. The CPU offers flexibility with a 10-core setup featuring 6 high-performance cores and 4 high-efficiency cores, or a 12-core variant with 8 high-performance cores and 4 high-efficiency cores, scaling up from the base M2's architecture to handle more demanding multitasking and creative applications. The integrated GPU provides 16 or 19 cores, enabling advanced graphics processing suitable for and without discrete GPUs. Memory support in the M2 Pro emphasizes high-bandwidth unified architecture, configurable to 16 GB or 32 GB of fast, low-latency with GB/s , doubling the base M2's capacity for smoother handling of large datasets and multiple applications. This setup allows connectivity for up to three external displays—two at 6K resolution at 60 Hz via and one at at 60 Hz via —facilitating expansive workspaces for professionals in and . The Pro includes an enhanced media engine with for H.264, HEVC, ProRes, and ProRes RAW encoding and decoding, supporting multiple streams of 8K ProRes video to streamline high-resolution . Introduced on January 17, , alongside the 14-inch and 16-inch models, it also powers the , bridging consumer-level tasks with pro-grade demands by offering scalable performance that exceeds the base while remaining more power-efficient than higher-end variants.

M2 Max

The M2 Max is the high-end variant of the Apple M2 (), designed for demanding creative workflows such as professional , , and tasks that require substantial computational resources. Fabricated with 67 billion transistors on TSMC's second-generation , it integrates a 12-core CPU consisting of eight high-performance cores and four high-efficiency cores, with the performance cores capable of reaching up to 3.68 GHz. The GPU scales up to 38 cores (configurable to 30 cores), enabling peak floating-point performance of approximately 13.6 teraflops (TFLOPS) in single-precision operations, which supports accelerated graphics processing for complex and simulations. Memory configuration in the M2 Max supports 32 GB to 96 GB of unified LPDDR5 memory with a bandwidth of 400 GB/s, allowing seamless data sharing between CPU, GPU, and Neural Engine for memory-intensive applications like 8K video editing or large-scale 3D modeling. It also drives up to four external displays simultaneously—three at 6K resolution and 60 Hz via Thunderbolt ports, plus one at 4K resolution and 144 Hz via HDMI—facilitating multi-monitor setups for creative professionals. The integrated 16-core Neural Engine handles up to 15.8 tera operations per second for AI-accelerated tasks, enhancing features like object recognition in media workflows. The M2 Max incorporates a hardware-accelerated ray tracing engine in its GPU architecture, introduced in the M2 series, which optimizes real-time rendering and lighting simulations in 3D applications. This makes it particularly suited for professional software like and , where ray-traced effects improve visual fidelity without compromising workflow speed. Debuting in the 16-inch in January 2023, the M2 Max strikes a balance between high performance and portability in a form factor, positioning it above the intermediate M2 Pro for users needing extreme graphics capabilities.

M2 Ultra

The M2 Ultra is the highest-end variant in Apple's M2 series of system on chips (SoCs), designed for demanding professional workloads in desktop and workstation environments. It achieves its performance through an innovative multi-die architecture that combines two M2 Max dies into a single package using Apple's proprietary UltraFusion interconnect. This configuration results in a total of 134 billion transistors, enabling extreme scaling for tasks such as , , and inference. The CPU subsystem features 24 cores, comprising 16 high-performance cores and 8 high-efficiency cores, which provide up to 20% faster multi-core performance compared to the preceding . The integrated GPU scales to 60 or 76 cores, delivering up to 27.2 teraflops of floating-point performance to handle complex graphics and compute workloads efficiently. Complementing these are a 32-core Neural Engine capable of 31.6 trillion operations per second and a dedicated media engine for hardware-accelerated encoding and decoding of formats like ProRes and H.264. The chip supports up to 192 GB of unified LPDDR5 with 800 GB/s , allowing seamless sharing between CPU, GPU, and other accelerators for memory-intensive applications. Central to the M2 Ultra's design is the UltraFusion interconnect, a high-speed silicon interposer that links the two dies with over 10,000 signals, achieving more than 2.5 TB/s of low-latency . This enables the chip to operate as a cohesive unit, supporting server-grade capabilities like massive without the typical penalties of multi-chip configurations. Display output supports up to eight external displays simultaneously, such as up to eight at at 60 Hz or six at 6K at 60 Hz via ports, depending on the device configuration. Apple launched the M2 Ultra in June 2023 as the culmination of the M2 series, powering the updated and desktops. These systems leverage the chip's capabilities for pro-level creativity and productivity, marking the end of the M2 lineup before the transition to the M3 generation.

Devices Using M2 Series

Macintosh Computers

The Apple M2 series powers a range of Macintosh computers, spanning laptops, desktops, and workstations, introduced between 2022 and 2023 to continue the transition from processors to . These devices leverage the M2 chip's efficiency for everyday computing, creative workflows, and professional tasks, with configurations tailored to different form factors. The , Apple's fanless ultraportable laptop, was refreshed with the base chip in a redesigned 13-inch model announced on June 6, 2022, and available starting July 8, 2022. A 15-inch variant followed, announced on June 5, 2023, and available from June 13, 2023, offering a larger display while maintaining the fanless design for silent operation. The 13-inch MacBook Pro, the final model in that size, incorporated the base M2 chip and was announced alongside the MacBook Air on June 6, 2022, with availability starting June 17, 2022; it served as a key step in completing the Apple silicon transition for compact professional laptops. Higher-end MacBook Pro models adopted M2 Pro and M2 Max variants in 14-inch and 16-inch sizes, featuring mini-LED Liquid Retina XDR displays; these were announced on , 2023, and available from , 2023, targeting users needing enhanced graphics and connectivity. The , a compact desktop, was updated with base M2 and M2 Pro options, announced on , 2023, and available from , 2023, emphasizing its small footprint for home and office setups. The , a pro-oriented tower, integrated M2 Max and M2 Ultra chips, announced on June 5, 2023, and available from June 13, 2023, to support demanding workflows in a mid-form-factor . Finally, the workstation adopted the M2 Ultra chip exclusively, announced on June 5, 2023, and available from June 13, 2023, with modular PCIe expansion for enterprise and creative professionals. As of 2025, M2-based Macs remain fully supported with software updates, including macOS Sequoia, but Apple has phased out production in favor of M3 and M4 series models, with some configurations available only through refurbished channels.

iPad Models

The Apple M2 chip powers several models, bringing enhanced performance to portable, touch-optimized tablets designed for creative and productivity workflows under . The 4th-generation 11-inch , released in October 2022, features the base chip paired with a offering 120Hz refresh rates for smooth interactions. It supports the 2nd-generation with advanced hover capabilities for precise drawing and . The 6th-generation 12.9-inch , also released in October 2022, incorporates the base chip and a mini-LED backlit Liquid Retina XDR display for superior contrast and content viewing. It includes for secure biometric authentication, making it suitable for professional tasks like and applications. The 6th-generation iPad Air, available in 11-inch and 13-inch sizes and released in May 2024, uses the base M2 chip to deliver desktop-class capabilities in a lighter . Both variants feature landscape-oriented Liquid Retina displays and a front-facing Center Stage camera for dynamic video calls that automatically adjust framing. These models share key specifications including 8 of as standard (with 16 on higher-storage iPad Pro configurations), storage options up to 2 TB, and high-speed connectivity via /USB 4 ports on the or USB- with 10 Gb/s transfer speeds on the . The unified of the enhances multitasking by allowing seamless data sharing between CPU, GPU, and Neural Engine. As of November 2025, M2-equipped iPads remain viable mid-range options for users seeking balanced performance in tablets, even with the introduction of M3 variants in newer models.

Other Apple Devices

The Apple Vision Pro, released in February 2024, represents Apple's first spatial computer and the only non-Mac or iPad device to incorporate the M2 chip as of late 2025. This mixed-reality headset features a single M2 chip with an 8-core CPU (4 performance cores and 4 efficiency cores), a 10-core GPU, and a 16-core Neural Engine, paired with a dedicated R1 co-processor that handles real-time processing of sensor inputs with 12-millisecond photon-to-photon latency. The M2 enables standalone performance for running visionOS, Apple's operating system for spatial computing, while the R1 manages data from 12 cameras, five sensors, and six microphones to support immersive experiences. Equipped with dual micro-OLED displays offering approximately per eye and up to 100 Hz , the Vision Pro uses the for rendering high-resolution passthrough video of the real world and overlaying elements. Eye and hand tracking are facilitated by four eye-tracking cameras and infrared flood illuminators for Optic ID authentication, along with and TrueDepth cameras for precise , allowing users to interact without physical controllers. The device comes standard with 16 GB of unified memory and storage options of 256 GB, 512 GB, or 1 TB, supporting a range of applications including productivity tools, entertainment, and optimized for the headset's immersive environment. The M2's integration in the Vision Pro emphasizes efficient compute for vision-based tasks, such as environmental mapping and content generation, distinguishing it from traditional computing devices by blending digital interfaces with the physical space. No other major Apple devices featuring the M2 series were released in 2025, as the Vision Pro lineup transitioned to the more advanced M5 chip later that year.

References

  1. [1]
    Apple unveils M2 with breakthrough performance and capabilities
    50 percent more than M1 — and can be configured with up to 24GB of fast unified memory. Faster ...
  2. [2]
    Apple introduces next-generation iPad Pro, supercharged by the M2 ...
    Oct 18, 2022 · The new iPad Pro features a next-level Apple Pencil hover experience, ProRes video capture, superfast Wi-Fi 6E, and powerful features in iPadOS 16.Apple (CA) · iPad Pro with the M2 chip · Apple (AU) · Apple (SG)
  3. [3]
    Apple introduces new Mac mini with M2 and M2 Pro
    Jan 17, 2023 · With the M2 chip, Mac mini is even more powerful, capable, and affordable with a new starting price of just $599. The new M2 Pro chip delivers ...
  4. [4]
    All-new MacBook Air with M2 available to order starting Friday, July 8
    Jul 6, 2022 · Apple today announced the completely redesigned MacBook Air with M2, will be available to order beginning Friday, July 8, at 5 a.m. PDT.
  5. [5]
    13-inch MacBook Pro with M2 available to order starting Friday ...
    Jun 14, 2022 · On Friday, June 17, at 5 a.m. PDT, the updated 13-inch MacBook Pro with M2 will be available to customers to order on apple.com, the Apple Store ...
  6. [6]
    Apple unveils MacBook Pro featuring M2 Pro and M2 Max
    Jan 17, 2023 · The new MacBook Pro models with M2 Pro and M2 Max are available to order today, January 17, on apple.com/store and in the Apple Store app in 27 ...NewsroomApple unveils MacBook Pro ...
  7. [7]
    Apple introduces M2 Ultra
    Jun 5, 2023 · Apple today announced M2 Ultra, a new system on a chip (SoC) that delivers huge performance increases to the Mac and completes the M2 ...Apple (SG) · Apple (CA) · Apple (HK) · Apple (MY)
  8. [8]
    Apple unveils the redesigned 11-inch and all-new 13-inch iPad Air ...
    May 7, 2024 · Customers can order the new iPad Air with M2 starting today, May 7, on apple.com/store, and in the Apple Store app in 29 countries and regions, ...Newsroom · Apple (AU) · Apple (BH) · Apple (EG)
  9. [9]
    Apple Vision Pro available in the U.S. on February 2
    Jan 8, 2024 · Apple Vision Pro will be available beginning Friday, February 2, at all U.S. Apple Store locations and the U.S. Apple Store online.
  10. [10]
    Apple unveils all-new MacBook Air, supercharged by the new M2 chip
    Jun 6, 2022 · Apple today introduced a completely redesigned MacBook Air and an updated 13-inch MacBook Pro, both powered by the new M2 chip.
  11. [11]
    Apple unveils M2 Pro and M2 Max: next-generation chips for next ...
    Jan 17, 2023 · M2 Pro scales up the architecture of M2 to deliver an up to 12-core CPU and up to 19-core GPU, together with up to 32GB of fast unified memory.
  12. [12]
    Why the M2 is more advanced that it seemed
    Jan 15, 2024 · Mercifully, Arm defines its ISA in versions. CPU cores in M1 chips use ARMv8.5-A, while those in M2 and M3 chips use ARMv8.6-A, and Arm ...<|separator|>
  13. [13]
    Apple M2 Processor - Benchmarks and Specs - Notebookcheck
    Jun 29, 2022 · It offers 8 cores divided in four performance cores and four power-efficiency cores. The big cores offer 192 KB instruction cache, 128 KB data ...
  14. [14]
    MacBook Air (15-inch) Review: The Big Apple | Tom's Hardware
    Rating 4.0 Jul 15, 2023 · We can't log the M2's clock speeds (Cinebench estimates 3.5 GHz at single-core and 3.2 GHz at multi-core, but take that with a grain of salt), ...
  15. [15]
    Speed or security? Speculative execution in Apple silicon
    Feb 25, 2025 · This article explains some techniques that are used in the CPU cores of Apple silicon chips, to improve processing speed by making execution more efficient.Out-Of-Order Execution · Load Address Prediction · Load Value PredictionMissing: AMX SIMD
  16. [16]
    The Elusive Apple Matrix Coprocessor (AMX) - Engineering Deficiency
    Dec 30, 2024 · We can compare the performance between SIMD operations performed by Arm NEON and Apple's AMX by testing a few different strategies, first ...
  17. [17]
    [PDF] Performance Analysis of the Apple AMX Matrix Accelerator
    This thesis tackles three practical questions regarding AMX: (1) What are the achievable data- movement and compute throughputs on modern Apple Silicon? (2) How ...
  18. [18]
    Mac Studio (2023) - Tech Specs - Apple Support
    Apple M2 Max chip. 12-core CPU with 8 performance cores and 4 efficiency cores. 30-core GPU. 16-core Neural Engine. 400GB/s memory bandwidth. Media engine.<|separator|>
  19. [19]
    Apple Introduces M2 Processor: 8-Core CPU, 10-Core GPU, up to ...
    Jun 6, 2022 · The high-performance cores have a beefed-up cache, with 16MB of shared L2 cache compared to M1's 12MB L2. The four efficiency cores have an ...
  20. [20]
    Don't Believe the Hype: Apple's M2 GPU is No Game Changer
    Oct 6, 2022 · (Note that the RTX 3050 is about 15% faster in our ray tracing test suite.) Architecturally, Apple's GPUs look similar to AMD's in terms of ...
  21. [21]
    [PDF] Metal Feature Set Tables | Apple Developer
    Oct 20, 2025 · Tile shaders. Metal4. Apple4. —. Imageblock sample coverage control. Metal4 ... Variable rasterization rate 7. Metal4. Apple6. Varies. Vertex ...
  22. [22]
    MacBook Air (M2, 2022) - Tech Specs - Apple Support
    Apple M2 chip. 8-core CPU with 4 performance cores and 4 efficiency cores. 8-core GPU. 16-core Neural Engine. 100GB/s memory bandwidth. Configurable to M2 with ...
  23. [23]
    Apple M2 Max (38 Core) Benchmarks & Specs - CPU-Monkey.com
    FP32 Benchmark (AIDA64) ; Apple M4 Max (32 Core) TBDR (Metal 3) - 512 CU @ 1.58 GHz. 13.64 TFLOPS ; Apple M2 Max (38 Core) 608 CU @ 1.40 GHz. 13.49 TFLOPS ; AMD ...
  24. [24]
    Apple M2 Ultra: What makes it special, and for whom? - ZDNET
    Jun 6, 2023 · Apple's M2 Ultra takes two M2 Max chips -- with their 12 CPU cores, up to 38 GPU cores, up to 96GB of unified memory, and 400GB/s memory bandwidth.
  25. [25]
  26. [26]
    Deploying Transformers on the Apple Neural Engine
    Jun 6, 2022 · The 16-core Neural Engine on the A15 Bionic chip on iPhone 13 Pro has a peak throughput of 15.8 teraflops, an increase of 26 times that of ...
  27. [27]
    Performance — Guide to Core ML Tools - Apple
    For a model that is primarily running on the Neural Engine, sparsity typically helps in improving latency. This is made possible by two factors.Missing: M2 support
  28. [28]
    MacBook Pro (13-inch, M2, 2022) - Technical Specifications
    Chip. Apple M2 chip. 8-core CPU with 4 performance cores and 4 efficiency cores. 10-core GPU. 16-core Neural Engine. 100GB/s memory bandwidth. Media engine.
  29. [29]
    The M2's Unique Combination of Unified Memory and GPU ...
    Jun 9, 2022 · The M2 uses LPDDR5-6400 memory that supports 100GB/second of memory bandwidth, which is a 50% increase in bandwidth over the M1.
  30. [30]
    MacBook Pro (16-inch, 2023) - Technical Specifications
    Chip. Apple M2 Pro chip. 12-core CPU with 8 performance cores and 4 efficiency cores. 19-core GPU. 16-core Neural Engine. 200GB/s memory bandwidth.
  31. [31]
    A Brief Look at Apple's M2 Pro iGPU - Chips and Cheese
    Oct 31, 2023 · Like the M1, M2 Pro's iGPU cache hierarchy starts with a tiny 8 KB L1 cache. It's about as fast as the 32 KB L1 vector cache on Phoenix.Missing: Firestorm Icestorm
  32. [32]
    5nm Technology - Taiwan Semiconductor Manufacturing Company ...
    These include N5P, N4P, and N4C, which offer better power, performance, density, and more cost-effective advantages; N4X, a process tailored for HPC ...Missing: Apple M2
  33. [33]
    TSMC N5 Process Technology Wiki - SemiWiki
    Jul 14, 2025 · N5P, Performance-enhanced N5; ~5% speed boost or 10% lower power, 2021 ; N4, Optical shrink of N5; compatible design rules, better density, 2022.
  34. [34]
  35. [35]
    Apple M2 Pro SoC - Yole Group
    Aug 3, 2023 · The System-in-Package (SiP) with Ball-Grid-Array (BGA) packaging technology is used to assemble the SoC die with DRAM packages and capacitors.
  36. [36]
    M2 Pro SoC, the Apple's path of innovative advancements
    Aug 16, 2023 · The CPU cores used in the M2 Pro are the new Avalanche and Blizzard, whereas the M1 series uses Firestorm and Icestorm cores. The number of ...
  37. [37]
    Apple M2 Ultra Processor TSMC InFO-L Package Technology ...
    This advancing packaging quick look report (APQ) provides insight on the advanced packaging innovations used in the manufacturing of the Apple M2 Ultra ...
  38. [38]
    InFO Advanced Packaging | Integrated Fan-Out by TSMC
    InFO is TSMC's fan-out wafer-level packaging, used in Apple's A- and M-series chips. Learn about process, features, applications, customers, and outlook.
  39. [39]
    MacBook Air (2022) Benchmarks - Geekbench Browser
    The MacBook Air (2022) with an Apple M2 processor scores 2,586 for single-core performance and 9,670 for multi-core performance in the Geekbench 6 CPU Benchmark ...
  40. [40]
    MacBook Pro (14-inch, 2023) Benchmarks - Geekbench Browser
    The MacBook Pro (14-inch, 2023) with an Apple M2 Pro processor scores 2,656 for single-core performance and 14,438 for multi-core performance in the Geekbench 6 ...
  41. [41]
    Mac Studio (2023) Benchmarks - Geekbench Browser
    The Mac Studio (2023) with an Apple M2 Ultra processor scores 2,776 for single-core performance and 21,388 for multi-core performance in the Geekbench 6 CPU ...
  42. [42]
    iPad Air 13-inch (M2) Benchmarks - Geekbench Browser
    CPU Benchmark Scores. 2594. Single-Core Score. 9836. Multi-Core Score. GPU Benchmark Scores. 42085. Metal Score. Device Information. Name, iPad Air 13-inch (M2).
  43. [43]
    Apple M2 Ultra GPU Outpaces RTX 4070 Ti in Early Compute ...
    Jun 10, 2023 · For a direct Geekbench 6 OpenCL comparison, the Apple M2 Ultra Open CL scores of about 155,000 are much closer to PC GPUs like the Nvidia RTX A ...
  44. [44]
    Apple M2 Review | TechSpot
    Rating 90% · Review by Tim SchiesserJul 12, 2022 · But even for exporting, the M2 is an excellent choice, delivering the performance of an integrated GPU 45W solution at just 20-25W. Premiere ...
  45. [45]
    M2 Power Consumption - MacRumors Forums
    Aug 30, 2022 · The M2 MacBook Air can use over 35W when under heavy load. But if the load is low, I frequently find that my M2 MacBook Air is using less than 4W.Missing: TDP | Show results with:TDP
  46. [46]
    No, throttling and overheating isn't a problem on M2 MacBook Air
    Free 14-day returnsAug 7, 2022 · The MacBook Air throttles when doing CPU-intensive tasks that are often done by users doing “serious” work, often in a professional setting.Missing: behavior | Show results with:behavior
  47. [47]
    How many displays can be connected to Mac mini - Apple Support
    May 9, 2025 · Mac mini (2023) with M2 Pro chip supports up to three external displays simultaneously, depending on the resolution and refresh rate of each ...Mac mini (2024) with M4 chip · Mac mini (2023) with M2 chip
  48. [48]
    Mac mini (2023) - Tech Specs - Apple Support
    Apple M2 chip. 8-core CPU with 4 performance cores and 4 efficiency cores. 10-core GPU. 16-core Neural Engine. 100GB/s memory bandwidth. Media engine.
  49. [49]
    Apple M2 Chip: Everything You Need to Know - MacRumors
    Jul 14, 2023 · The M2 is Apple's next-generation System on a Chip (SoC) developed for use in Macs and iPads. It marks Apple's continued work to transition away ...
  50. [50]
    MacBook Pro (14-inch, 2023) - Technical Specifications
    Chip. Apple M2 Pro chip. 10-core CPU with 6 performance cores and 4 efficiency cores, 12-core CPU with 8 performance cores and 4 efficiency cores.
  51. [51]
    Apple Mac Studio "M2 Max" 12 CPU/38 GPU Specs - EveryMac.com
    Jun 5, 2023 · Apple does not provide a clockspeed, but third-party software reports that it runs around 3.68 GHz. It also has a 38-core GPU, a 16-core Neural ...
  52. [52]
    Apple M2 Max Processor - Benchmarks and Specs - Notebookcheck
    Jan 17, 2023 · CPU and GPU can both use the 49 MB SLC (System Level Cache). The unified memory (32, 64, or 96 GB LPDDR5-6400) next to the chip is connected by ...
  53. [53]
    Mac Studio - Technical Specifications - Apple
    Free delivery Free 14-day returnsHardware-accelerated H.264, HEVC, ProRes, and ProRes RAW · Two video decode engines · Four video encode engines · Four ProRes encode and decode engines · AV1 decode.
  54. [54]
    Apple M2 Ultra (76 Core) Benchmarks & Specs - CPU-Monkey.com
    Apple M2 Ultra (76 Core) 1216 CU @ 1.40 GHz. 26.98 TFLOPS ; AMD Radeon 8050S Graphics RDNA 3.5 - 32 CU @ 2.80 GHz. 22.94 TFLOPS ; Apple M3 Ultra (60 Core) TBDR ( ...
  55. [55]
    Mac Pro (2023) - Tech Specs - Apple Support
    Chip. Apple M2 Ultra chip. 24-core CPU with 16 performance cores and 8 efficiency cores. 60-core GPU. 32-core Neural Engine. 800GB/s memory bandwidth.
  56. [56]
    Apple introduces the 15-inch MacBook Air
    Jun 5, 2023 · It will begin arriving to customers, and in Apple Store locations and Apple Authorized Resellers, beginning Tuesday, June 13.
  57. [57]
    Apple unveils new Mac Studio and brings Apple silicon to Mac Pro
    Jun 5, 2023 · Mac Studio and Mac Pro are available to order today, with availability beginning Tuesday, June 13. “The new Mac Studio and Mac Pro with Apple ...
  58. [58]
    macOS Sequoia is compatible with these computers - Apple Support
    Sep 15, 2025 · MacBook Air (15-inch, M2, 2023). MacBook Air (M2, 2022). MacBook Air ... iMac (24-inch, 2024, Four ports). iMac (24-inch, 2024, Two ports).<|separator|>
  59. [59]
    iPad Pro 11-inch (4th generation) - Technical Specifications
    Apple M2 chip. 8-core CPU with 4 performance cores and 4 efficiency cores. 10-core GPU. 16-core Neural Engine. 100GB/s memory bandwidth. 8GB RAM on models with ...
  60. [60]
    iPad Pro 12.9-inch (6th generation) - Technical Specifications
    Apple M2 chip. 8-core CPU with 4 performance cores and 4 efficiency cores. 10-core GPU. 16-core Neural Engine. 100GB/s memory bandwidth. 8GB RAM on models with ...
  61. [61]
    iPad Air - Technical Specifications - Apple
    In the Box. iPad Air; USB‑C Charge Cable (1 meter); 20W USB‑C Power Adapter ... Activate hands-free with only your voice using “Siri” or “Hey Siri,” or use Type ...
  62. [62]
    Compare iPad Models - Apple
    4.7 15K · Free delivery · Free 14-day returnsCompare resolution, size, weight, performance, battery life, and storage of iPad Pro, iPad Air, iPad, and iPad mini models.
  63. [63]
    Identify your iPad model - Apple Support
    Oct 21, 2025 · iPad Air 11-inch (M3). 2025 iPad Air 11-inch. Year: 2025. Capacity: 128 ... iPad Air 13-inch (M2). Year: 2024. Capacity: 128 GB, 256 GB, 512 ...
  64. [64]
    Apple Vision Pro - Tech Specs
    Apple M2 Chip. 8‑core CPU with 4 performance cores and 4 efficiency cores. 10‑core GPU. 16‑core Neural Engine. 16GB unified memory ; Apple R1 Chip. 12‑ ...
  65. [65]
    Introducing Apple Vision Pro: Apple's first spatial computer
    Jun 5, 2023 · M2 delivers unparalleled standalone performance, while the brand-new R1 chip processes input from 12 cameras, five sensors, and six ...Apple (AU) · Apple (CA) · Apple (UK) · Apple (SG)
  66. [66]
    Apple Vision Pro upgraded with the M5 chip and Dual Knit Band
    Oct 15, 2025 · PRESS RELEASE October 15, 2025. Apple Vision Pro upgraded with the powerful M5 chip and comfortable Dual Knit Band. The latest version ...