Apple launches next-gen Apple Silicon chips: M6 and M5 Ultra

Chance Miller | Aug 25 2026 - 6:00 am PT

Apple has unveiled two new Apple Silicon chips today. The M6 chip debuts in a new Mac mini model and marks Apple’s first 2nm processor. The M5 Ultra launches in a refreshed Mac Studio and is Apple’s most powerful chip ever.

Apple’s new M6 chip

The M6 is Apple’s first 2-nanometer chip, which the company says increases transistor density and power efficiency. This allows it to upgrade compute blocks without increasing die size.

The M6 features a 12-core CPU, two more than the M5 chip. Notably, it’s Apple’s first processor with all three CPU core types. That includes two super cores, four performance cores, and six efficiency cores.

Super cores prioritize maximum single-threaded performance and are Apple’s most powerful core type. Performance cores are optimized for demanding multithreaded work, and efficiency cores handle background tasks.

All told, Apple says this means M6 has “the world’s fastest single-threaded performance” and offers “up to 1.2x faster multithreaded performance as compared to M5.”

M6 features a 12-core GPU, which is two more cores than M5. There’s a Neural Accelerator in each core. Apple says this enables a 30% increase in peak GPU compute for AI compared to M5. The M6 GPU also features updates to its shader core architecture, Dynamic Caching, and hardware-accelerated ray tracing.

M6 supports up to 32GB of unified memory with up to 170GB/s of unified memory bandwidth. That’s up to 10% faster than M5.

Additionally, M6 can process FP8 natively in hardware, whereas M5 handles FP8 through software. FP8 is an 8-bit format designed to make AI workloads faster and more memory-efficient

M6 specs and benchmarks:

CPU: Up to 1.2x faster multithreaded performance than M5 and 2.4x faster than M1.
GPU AI compute: Nearly 30% higher peak GPU compute for AI than M5 and more than 8x higher than M1.
Geometry performance: 50% higher geometry rates for complex graphics.
Neural Engine: The Dual 16-core Neural Engine delivers up to 2x the peak compute of previous generations.
Memory bandwidth: Up to 170GB/s, 10% higher than M5 and 2.5x M1.

M6 is launching today in the new Mac mini, which you can read more about in our dedicated coverage.

M5 Ultra

At the high end, Apple has announced the M5 Ultra. The company says this is its “most powerful chip ever.” The headlining change is that the M5 Ultra uses a next-generation UltraFusion technology.

Apple explains that the new UltraFusion technology connects two dual-die M5 Max chips, resulting in its first quad-die chip architecture. The new UltraFusion design delivers more than 4.4TB/s of inter-die bandwidth and over 6x higher connection density, allowing all four dies to behave as a single unified processor.

M5 Ultra offers an up-to-36-core CPU with 12 super cores and 24 performance cores. Apple says this enables up to 1.25x higher single-threaded performance and up to 1.3x higher multithreaded performance compared to M3 Ultra.

For graphics, the M5 Ultra offers a next-generation GPU with up to 80 cores, with a Neural Accelerator in each core. Apple says M5 Ultra offers up to 4.5x peak GPU compute for AI compared to M3 Ultra.

More M5 Ultra GPU specs include:

Apple’s latest shader core with second-generation dynamic caching
Hardware-accelerated mesh shading
Third-generation ray tracing

All in all, Apple says you can expect up to 40% faster graphics performance with M5 Ultra compared to M3 Ultra.

M5 Ultra supports up to 512GB of unified memory with up to 1.2TB/s of unified memory bandwidth, which is 50% higher than M3 Ultra.

M5 Ultra specs and benchmarks

CPU: Up to 1.25x faster single-threaded performance and 1.3x faster multithreaded performance than M3 Ultra.
GPU AI compute: Up to 4.5x the peak GPU compute for AI compared to M3 Ultra and over 6x compared to M1 Ultra.
Graphics: Up to 40% faster graphics performance than M3 Ultra.
Memory bandwidth: 1.2TB/s, which is 50% higher than M3 Ultra.

M5 Ultra is launching today in the new Mac Studio, which you can learn more about in our full coverage.