Follow us
Share link
Submit benchmark
Apple M4 Max (16-CPU 40-GPU) vs Apple M3 Ultra (28-CPU 60-GPU)
Last updated:
CPU comparison with benchmarks
|
 |
|
| Apple M4 Max (16-CPU 40-GPU) | Apple M3 Ultra (28-CPU 60-GPU) | |
CPU comparisonApple M4 Max (16-CPU 40-GPU) or Apple M3 Ultra (28-CPU 60-GPU) - which processor is faster? In this comparison we look at the differences and analyze which of these two CPUs is better. We compare the technical data and benchmark results.
The Apple M4 Max (16-CPU 40-GPU) has 16 cores with 16 threads and clocks with a maximum frequency of 4.50 GHz. Up to 128 GB of memory is supported in 8 memory channels. The Apple M4 Max (16-CPU 40-GPU) was released in Q4/2024. The Apple M3 Ultra (28-CPU 60-GPU) has 28 cores with 28 threads and clocks with a maximum frequency of 4.06 GHz. The CPU supports up to 256 GB of memory in 8 memory channels. The Apple M3 Ultra (28-CPU 60-GPU) was released in Q1/2025. |
||
| Apple M series (32) | Family | Apple M series (32) |
| Apple M4 (7) | CPU group | Apple M3 Ultra (2) |
| 4 | Generation | 3 |
| M4 | Architecture | M3 |
| Notebook | Segment | Desktop |
| Apple M3 Max (16-CPU 40-GPU) | Predecessor | Apple M2 Ultra (60-GPU) |
| -- | Successor | -- |
|
|
||
CPU Cores and Base FrequencyThe Apple M4 Max (16-CPU 40-GPU) is a 16 core processor with a clock frequency of 0.70 GHz (4.50 GHz). The Apple M3 Ultra (28-CPU 60-GPU) has 28 CPU cores with a clock frequency of 0.70 GHz (4.06 GHz). |
||
| Apple M4 Max (16-CPU 40-GPU) | Characteristic | Apple M3 Ultra (28-CPU 60-GPU) |
| 16 | Cores | 28 |
| 16 | Threads | 28 |
| hybrid (big.LITTLE) | Core architecture | hybrid (big.LITTLE) |
| No | Hyperthreading | No |
| No | Overclocking ? | No |
| 0.70 GHz (4.50 GHz) 12x Donan P-Core |
A-Core | 0.70 GHz (4.06 GHz) 20x Palma P-Core |
| 0.74 GHz (2.85 GHz) 4x Donan E-Core |
B-Core | 0.74 GHz (2.75 GHz) 8x Palma E-Core |
NPU AI performanceThe performance values of the processor's AI unit. The isolated NPU performance is specified here, the total AI performance (NPU+CPU+iGPU) can be higher. Processors with support for artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. |
||
| Apple M4 Max (16-CPU 40-GPU) | Characteristic | Apple M3 Ultra (28-CPU 60-GPU) |
| Apple Neural Engine | AI hardware | Apple Neural Engine |
| 16 Neural cores @ 38 TOPS | AI specifications | 32 Neural cores @ 70 TOPS |
| -- | NPU + CPU + iGPU | -- |
Integrated graphics (iGPU)The integrated graphics unit of a processor is not only responsible for the pure image output on the system, but can also significantly increase the efficiency of the system with the support of modern video codecs. |
||
| Apple M4 Max (40 Core) | GPU | Apple M3 Ultra (60 Core) |
| 0.39 GHz | GPU frequency | 0.39 GHz |
| 1.68 GHz | GPU (Turbo) | 1.40 GHz |
| -- | GPU Generation | -- |
| 3 nm | Technology | 3 nm |
| 3 | Max. displays | 8 |
| 640 | Compute units | 960 |
| 5120 | Shader | 7680 |
| Yes | Hardware Raytracing | Yes |
| No | Frame Generation | No |
| 32 GB | Max. GPU Memory | 256 GB |
| -- | DirectX Version | -- |
Hardware codec supportA photo or video codec that is accelerated in hardware can greatly accelerate the working speed of a processor and extend the battery life of notebooks or smartphones when playing videos. |
||
| Apple M4 Max (40 Core) | GPU | Apple M3 Ultra (60 Core) |
| Decode / Encode | Codec h265 / HEVC (8 bit) | Decode / Encode |
| Decode / Encode | Codec h265 / HEVC (10 bit) | Decode / Encode |
| Decode / Encode | Codec h264 | Decode / Encode |
| Decode / Encode | Codec VP9 | Decode / Encode |
| Decode | Codec VP8 | Decode |
| Decode | Codec AV1 | Decode |
| Decode | Codec AVC | Decode |
| Decode | Codec VC-1 | Decode |
| Decode / Encode | Codec JPEG | Decode / Encode |
Memory & PCIeThe Apple M4 Max (16-CPU 40-GPU) supports a maximum of 128 GB of memory in 8 memory channels. The Apple M3 Ultra (28-CPU 60-GPU) can connect up to 256 GB of memory in 8 memory channels. |
||
| Apple M4 Max (16-CPU 40-GPU) | Characteristic | Apple M3 Ultra (28-CPU 60-GPU) |
| LPDDR5X-8533 | Memory | LPDDR5-6400 |
| 128 GB | Max. Memory | 256 GB |
| 8 (Octa Channel) | Memory channels | 8 (Octa Channel) |
| 546.0 GB/s | Max. Bandwidth | 818.7 GB/s |
| No | ECC | No |
| 52.00 MB | L2 Cache | 80.00 MB |
| -- | L3 Cache | -- |
| 4.0 | PCIe version | 4.0 |
| -- | PCIe lanes | -- |
| -- | PCIe Bandwidth | -- |
Thermal ManagementThe TDP (Thermal Design Power) of a processor specifies the required cooling solution. The Apple M4 Max (16-CPU 40-GPU) has a TDP of --, that of the Apple M3 Ultra (28-CPU 60-GPU) is 115 W. |
||
| Apple M4 Max (16-CPU 40-GPU) | Characteristic | Apple M3 Ultra (28-CPU 60-GPU) |
| -- | TDP (PL1 / PBP) | 115 W |
| -- | TDP (PL2) | -- |
| -- | TDP up | -- |
| -- | TDP down | -- |
| 100 °C | Tjunction max. | 100 °C |
Technical detailsThe Apple M4 Max (16-CPU 40-GPU) has a 52.00 MB cache, while the Apple M3 Ultra (28-CPU 60-GPU) cache has a total of 80.00 MB. |
||
| Apple M4 Max (16-CPU 40-GPU) | Characteristic | Apple M3 Ultra (28-CPU 60-GPU) |
| 3 nm | Technology | 3 nm |
| Monolithic | Chip design | Monolithic |
| Armv9-A (64 bit) | Instruction set (ISA) | Armv8-A (64 bit) |
| Rosetta 2 x86-Emulation, AVX2, SME | ISA extensions | Rosetta 2 x86-Emulation |
| -- | Socket | -- |
| Apple Virtualization Framework | Virtualization | Apple Virtualization Framework |
| Yes | AES-NI | Yes |
| macOS, iPadOS | Operating systems | macOS, iPadOS |
| Q4/2024 | Release date | Q1/2025 |
| -- | Release price | -- |
| show more data | show more data | |
16C 16T @ 0.70 GHz (4.50 GHz) buy now on Amazon and save!
28C 28T @ 0.70 GHz (4.06 GHz) buy now on Amazon and save!
|
||
Rate these processors
Average performance in benchmarks
⌀ Single core performance in 4 CPU benchmarks
⌀ Multi core performance in 1 CPU benchmarks
Cinebench 2024 Single-Core
The Cinebench 2024 benchmark is based on the Redshift rendering engine, which is also used in Maxon's 3D program Cinema 4D. The benchmark runs are each 10 minutes long to test whether the processor is limited by its heat generation.
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 4.50 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 4.06 GHz |
||
Cinebench R23 Single-Core
Cinebench R23 is the successor of Cinebench R20 and is also based on the Cinema 4 Suite. Cinema 4 is a worldwide used software to create 3D forms. The single-core test only uses one CPU core, the amount of cores or hyperthreading ability doesn't count.
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 4.50 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 4.06 GHz |
||
Geekbench 6 Single-Core
Geekbench 6 is a partial load benchmark for modern computers, notebooks and smartphones. In the single-core test, only the fastest CPU core is measured. The test run simulates the performance in practice.
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 4.50 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 4.06 GHz |
||
Geekbench 6 Multi-Core
The practical Geekbench 6 multi-core benchmark tests the system's performance under partial load. The processor's maximum power consumption is far from being used up.
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 0.70 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 3.60 GHz |
||
Geekbench 5, 64bit Single-Core
Geekbench 5 is a cross plattform benchmark that heavily uses the systems memory. A fast memory will push the result a lot. The single-core test only uses one CPU core, the amount of cores or hyperthreading ability doesn't count.
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 4.50 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 4.06 GHz |
||
iGPU - FP32 Performance (Single-precision GFLOPS)
The theoretical computing performance of the internal graphics unit of the processor with simple accuracy (32 bit) in GFLOPS. GFLOPS indicates how many billion floating point operations the iGPU can perform per second.
|
|
Apple M4 Max (16-CPU 40-GPU)
Apple M4 Max (40 Core) @ 1.68 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
Apple M3 Ultra (60 Core) @ 1.40 GHz |
||
AI performance (NPU)
The performance values of the processor's AI unit. The isolated NPU performance is given here, the total AI performance (NPU+CPU+iGPU) can be higher.
Processors with the support of artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. The performance is given in the number (trillions) of arithmetic operations per second (TOPS).
Processors with the support of artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. The performance is given in the number (trillions) of arithmetic operations per second (TOPS).
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 0.70 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 0.70 GHz |
||
Cinebench 2024 Multi-Core
The Multi-Core test of the Cinebench 2024 benchmark uses all cpu cores to render using the Redshift rendering engine, which is also used in Maxons Cinema 4D. The benchmark run is 10 minutes long to test whether the processor is limited by its heat generation.
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 4.50 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 4.06 GHz |
||
Cinebench R23 Multi-Core
Cinebench R23 is the successor of Cinebench R20 and is also based on the Cinema 4 Suite. Cinema 4 is a worldwide used software to create 3D forms. The multi-core test involves all CPU cores and taks a big advantage of hyperthreading.
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 0.70 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 3.60 GHz |
||
Geekbench 5, 64bit Multi-Core
Geekbench 5 is a cross plattform benchmark that heavily uses the systems memory. A fast memory will push the result a lot. The multi-core test involves all CPU cores and taks a big advantage of hyperthreading.
|
|
Apple M4 Max (16-CPU 40-GPU)
16C 16T @ 0.70 GHz |
||
|
|
Apple M3 Ultra (28-CPU 60-GPU)
28C 28T @ 3.60 GHz |
||
Devices using this processor |
|
| Apple M4 Max (16-CPU 40-GPU) | Apple M3 Ultra (28-CPU 60-GPU) |
| Unknown | Apple Mac Studio (2025) |
Popular comparisons containing this CPUs
back to index