AMD EPYC 9684X vs Apple M2 Ultra (60-GPU)

Last updated:

CPU comparison with benchmarks


AMD EPYC 9684X CPU1 vs CPU2 Apple M2 Ultra (60-GPU)
AMD EPYC 9684X Apple M2 Ultra (60-GPU)

CPU comparison

AMD EPYC 9684X or Apple M2 Ultra (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 AMD EPYC 9684X has 96 cores with 192 threads and clocks with a maximum frequency of 3.70 GHz. Up to 6144 GB of memory is supported in 12 memory channels. The AMD EPYC 9684X was released in Q2/2023.

The Apple M2 Ultra (60-GPU) has 24 cores with 24 threads and clocks with a maximum frequency of 3.50 GHz. The CPU supports up to 192 GB of memory in 8 memory channels. The Apple M2 Ultra (60-GPU) was released in Q2/2023.
AMD EPYC (129) Family Apple M series (25)
AMD EPYC 9004 (21) CPU group Apple M2 (8)
4 Generation 2
Genoa / Genoa-X (Zen 4) Architecture M2
Desktop / Server Segment Mobile
-- Predecessor Apple M1 Ultra (48-GPU)
-- Successor --

CPU Cores and Base Frequency

The AMD EPYC 9684X has 96 CPU cores and can calculate 192 threads in parallel. The clock frequency of the AMD EPYC 9684X is 2.55 GHz (3.70 GHz) while the Apple M2 Ultra (60-GPU) has 24 CPU cores and 24 threads can calculate simultaneously. The clock frequency of the Apple M2 Ultra (60-GPU) is at 0.66 GHz (3.50 GHz).
AMD EPYC 9684X Characteristic Apple M2 Ultra (60-GPU)
96 Cores 24
192 Threads 24
normal Core architecture hybrid (big.LITTLE)
Yes Hyperthreading No
No Overclocking ? No
2.55 GHz (3.70 GHz)
96x Zen 4		 A-Core 0.66 GHz (3.50 GHz)
16x Avalanche
-- B-Core 0.60 GHz (2.42 GHz)
8x Blizzard

Artificial Intelligence and Machine Learning

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. Algorithms for ML improve their performance the more data they have collected via software. ML tasks can be processed up to 10,000 times faster than with a classic processor.
AMD EPYC 9684X Characteristic Apple M2 Ultra (60-GPU)
-- AI hardware Apple Neural Engine
-- AI specifications 32 Neural cores @ 31.6 TOPS

Internal Graphics

The AMD EPYC 9684X or Apple M2 Ultra (60-GPU) has integrated graphics, called iGPU for short. The iGPU uses the system's main memory as graphics memory and sits on the processor's die.
no iGPU GPU Apple M2 Ultra (60 Core)
GPU frequency 0.45 GHz
-- GPU (Turbo) 1.40 GHz
-- GPU Generation 2
Technology 5 nm
Max. displays 8
-- Compute units 960
-- Shader 7680
No Hardware Raytracing No
No Frame Generation No
-- Max. GPU Memory 192 GB
-- DirectX Version --

Hardware codec support

A 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.
no iGPU GPU Apple M2 Ultra (60 Core)
No Codec h265 / HEVC (8 bit) Decode / Encode
No Codec h265 / HEVC (10 bit) Decode / Encode
No Codec h264 Decode / Encode
No Codec VP9 Decode / Encode
No Codec VP8 Decode
No Codec AV1 No
No Codec AVC Decode
No Codec VC-1 Decode
No Codec JPEG Decode / Encode

Memory & PCIe

The AMD EPYC 9684X can use up to 6144 GB of memory in 12 memory channels. The maximum memory bandwidth is 460.8 GB/s. The Apple M2 Ultra (60-GPU) supports up to 192 GB of memory in 8 memory channels and achieves a memory bandwidth of up to 819.1 GB/s.
AMD EPYC 9684X Characteristic Apple M2 Ultra (60-GPU)
DDR5-4800 Memory LPDDR5-6400
6144 GB Max. Memory 192 GB
12 Memory channels 8 (Octa Channel)
460.8 GB/s Max. Bandwidth 819.1 GB/s
Yes ECC No
-- L2 Cache 72.00 MB
1,152.00 MB L3 Cache --
5.0 PCIe version 4.0
128 PCIe lanes 64
504.1 GB/s PCIe Bandwidth 126.0 GB/s

Thermal Management

The thermal design power (TDP for short) of the AMD EPYC 9684X is 400 W, while the Apple M2 Ultra (60-GPU) has a TDP of 80 W. The TDP specifies the necessary cooling solution that is required to cool the processor sufficiently.
AMD EPYC 9684X Characteristic Apple M2 Ultra (60-GPU)
400 W TDP (PL1 / PBP) 80 W
-- TDP (PL2) --
-- TDP up --
320 W TDP down --
100 °C Tjunction max. 100 °C

Technical details

The AMD EPYC 9684X is manufactured in 5 nm and has 1,152.00 MB cache. The Apple M2 Ultra (60-GPU) is manufactured in 5 nm and has a 72.00 MB cache.
AMD EPYC 9684X Characteristic Apple M2 Ultra (60-GPU)
5 nm Technology 5 nm
Chiplet Chip design Chiplet
x86-64 (64 bit) Instruction set (ISA) Armv8.5-A (64 bit)
SSE4.2, AVX2, AVX-512, BFLOAT16, VNNI ISA extensions Rosetta 2 x86-Emulation
SP5 Socket --
AMD-V, SVM Virtualization Apple Virtualization Framework
Yes AES-NI Yes
Windows Server 2022, Linux, Windows 11 Operating systems macOS, iPadOS
Q2/2023 Release date Q2/2023
14756 $ Release price --
show more data show more data


Rate these processors

Here you can rate the AMD EPYC 9684X to help other visitors make their purchasing decisions. The average rating is 5.0 stars (2 ratings). Rate now:
Here you can rate the Apple M2 Ultra (60-GPU) to help other visitors make their purchasing decisions. The average rating is 4.9 stars (166 ratings). Rate now:


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.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.70 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
126 (100%)

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.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.70 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
1918 (100%)

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.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.70 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
1695 (100%)

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.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.42 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
28570 (100%)

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.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.70 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
1940 (100%)

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.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.42 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
27860 (100%)

Geekbench 6 (Single-Core)

Geekbench 6 is a benchmark for modern computers, notebooks and smartphones. What is new is an optimized utilization of newer CPU architectures, e.g. based on the big.LITTLE concept and combining CPU cores of different sizes. The single-core benchmark only evaluates the performance of the fastest CPU core, the number of CPU cores in a processor is irrelevant here.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.70 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
2689 (100%)

Geekbench 6 (Multi-Core)

Geekbench 6 is a benchmark for modern computers, notebooks and smartphones. What is new is an optimized utilization of newer CPU architectures, e.g. based on the big.LITTLE concept and combining CPU cores of different sizes. The multi-core benchmark evaluates the performance of all of the processor's CPU cores. Virtual thread improvements such as AMD SMT or Intel's Hyper-Threading have a positive impact on the benchmark result.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.42 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
21450 (100%)

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.
AMD EPYC 9684X AMD EPYC 9684X
@ 0.00 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
Apple M2 Ultra (60 Core) @ 1.40 GHz
21300 (100%)

Estimated results for PassMark CPU Mark

Some of the CPUs listed below have been benchmarked by CPU-monkey. However the majority of CPUs have not been tested and the results have been estimated by a CPU-monkey’s secret proprietary formula. As such they do not accurately reflect the actual Passmark CPU mark values and are not endorsed by PassMark Software Pty Ltd.
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 3.42 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 3.50 GHz
48560 (100%)

CPU performance per watt (efficiency)

Efficiency of the processor under full load in the Cinebench R23 (multi-core) benchmark. The benchmark result is divided by the average energy required (CPU package power in watts). The higher the value, the more efficient the CPU is under full load.
AMD EPYC 9684X AMD EPYC 9684X
2.55 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
28,570 CB R23 MC @ 80 W
357 (100%)

Performance for Artificial Intelligence (AI) and Machine Learning (ML)

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).
AMD EPYC 9684X AMD EPYC 9684X
96C 192T @ 2.55 GHz
0 (0%)
Apple M2 Ultra (60-GPU) Apple M2 Ultra (60-GPU)
24C 24T @ 0.66 GHz
31.6 (100%)

Devices using this processor
AMD EPYC 9684X Apple M2 Ultra (60-GPU)
Unknown Unknown

Popular comparisons containing this CPUs

1. Apple M2 Ultra (60-GPU)Intel Core i9-13900K Apple M2 Ultra (60-GPU) vs Intel Core i9-13900K
2. Apple M2 Ultra (60-GPU)Apple M2 Ultra (76-GPU) Apple M2 Ultra (60-GPU) vs Apple M2 Ultra (76-GPU)
3. Apple M2 Ultra (60-GPU)Intel Core i9-14900K Apple M2 Ultra (60-GPU) vs Intel Core i9-14900K
4. Apple M2 Ultra (60-GPU)Apple M3 Max (16-CPU 40-GPU) Apple M2 Ultra (60-GPU) vs Apple M3 Max (16-CPU 40-GPU)
5. Apple M2 Ultra (60-GPU)AMD Ryzen 9 7950X3D Apple M2 Ultra (60-GPU) vs AMD Ryzen 9 7950X3D
6. Apple M2 Ultra (60-GPU)AMD Ryzen 9 7950X Apple M2 Ultra (60-GPU) vs AMD Ryzen 9 7950X
7. Apple M2 Ultra (60-GPU)Intel Core i7-13700K Apple M2 Ultra (60-GPU) vs Intel Core i7-13700K
8. Apple M2 Ultra (60-GPU)Intel Core i9-14900 Apple M2 Ultra (60-GPU) vs Intel Core i9-14900
9. Apple A17 ProApple M2 Ultra (60-GPU) Apple A17 Pro vs Apple M2 Ultra (60-GPU)
10. AMD EPYC 9754AMD EPYC 9684X AMD EPYC 9754 vs AMD EPYC 9684X


back to index