AMD EPYC 9654 vs AMD Ryzen 5 9600X Comparison

The AMD Ryzen 5 9600X and the AMD EPYC 9654 are both AMD processors, but they target completely different corners of the market. The data positions the Ryzen 5 9600X as a desktop part with a high boost clock, while the EPYC 9654 is a server behemoth with a massive core count. The benchmark results show a stark division of labor: the EPYC 9654 dominates in multi-threaded workloads, while the Ryzen 5 9600X holds its own in single-threaded and light-thread scenarios, despite the EPYC’s apparent wins in the head-to-head data.

Where Each One Wins

The division of wins is clear-cut based on the benchmark categories. The AMD EPYC 9654 is the undisputed champion in heavily multi-threaded applications. Its 96 cores and 192 threads allow it to achieve a Cinebench R23 multi-core score of 101675, which is 82.8% higher than the Ryzen 5 9600X’s score of 17528.5 in the same test. This makes the EPYC 9654 the obvious choice for server virtualization, large-scale data processing, and any workload that can scale across dozens of cores.

Conversely, the AMD Ryzen 5 9600X wins in scenarios that favor high clock speeds and low latency. While the head-to-head data only includes Cinebench tests, the broader benchmark suite for the Ryzen 5 9600X shows it excels in single-threaded tasks. Its 3DMark single-thread score of 1253 and PassMark single-thread score of 4570 are strengths, and its boost clock of 5.40 GHz is significantly higher than the EPYC 9654’s 3.70 GHz. This suggests the 9600X is better suited for gaming, general desktop responsiveness, and applications that rely on a few fast cores rather than many slower ones. The EPYC 9654’s lower base clock of 2.40 GHz and lower boost clock of 3.70 GHz make it less ideal for these latency-sensitive tasks.

The data also shows a difference in memory bandwidth that points to their intended uses. The EPYC 9654 supports twelve-channel memory with a bandwidth of 460.8 GB/s, which is massive for feeding 96 cores. The Ryzen 5 9600X, with its dual-channel memory and 89.6 GB/s bandwidth, is sufficient for a desktop workload but would bottleneck in a server environment. The EPYC 9654 also has a much larger L3 cache at 384 MB, compared to the 9600X’s 32 MB, which further supports its dominance in data-heavy server workloads.

Architecture Differences

The architectural gap between these two chips is vast. The Ryzen 5 9600X uses the Zen 5 architecture on a 4 nm process node, while the EPYC 9654 uses the older Zen 4 architecture on a 5 nm process node. This means the 9600X has a transistor density advantage, packing 8,315 million transistors into a 70.6 mm² die, whereas the EPYC 9654 spreads 78,840 million transistors across 12 dies, each measuring 72 mm². The newer process node for the 9600X contributes to its higher clock speeds and better single-thread performance.

The core counts are radically different, as expected. The Ryzen 5 9600X has 6 cores and 12 threads, while the EPYC 9654 has 96 cores and 192 threads. This 16x difference in core count is the primary driver of their performance profiles. Cache hierarchy also differs: the 9600X has 80 KB of L1 cache per core and 1 MB of L2 per core, while the EPYC 9654 has 64 KB of L1 per core and the same 1 MB of L2 per core. The L3 cache is the biggest difference, with the 9600X offering 32 MB shared and the EPYC 9654 offering 384 MB shared.

Other key differences include the socket and platform. The 9600X uses AMD Socket AM5, which is a desktop platform, while the EPYC 9654 uses AMD Socket SP5 for servers. The 9600X has 24 PCIe Gen 5 lanes, while the EPYC 9654 has 128 PCIe Gen 5 lanes, reflecting the server chip’s need for extensive I/O connectivity. The 9600X also includes integrated Radeon Graphics, while the EPYC 9654 has no integrated graphics, as servers typically use discrete GPUs or no display output. Both support ECC memory, but the 9600X is unlocked for overclocking, while the EPYC 9654 is locked.

Head-to-Head Benchmarks

The head-to-head data is one-sided, with the EPYC 9654 winning all four listed tests. In Cinebench R15 multi-core, the EPYC 9654 scores 10248, which is 73.7% higher than the Ryzen 5 9600X’s 2691. The single-core R15 test shows a similar pattern, with the EPYC 9654 scoring 1446 compared to the 9600X’s 342, a 76.3% delta. These are massive margins, but they need context.

The Cinebench R23 results reinforce the multi-core dominance. The EPYC 9654’s multi-core score of 101675 is 82.8% higher than the 9600X’s 17528.5. The single-core R23 test shows the EPYC 9654 scoring 14354, which is 84.8% higher than the 9600X’s 2183.5. At first glance, this seems to suggest the EPYC 9654 is even better at single-threaded tasks, which contradicts the clock speed advantage of the 9600X.

However, the data raises a question. The Ryzen 5 9600X’s Cinebench R23 single-core score of 2183.5 is lower than what its 5.40 GHz boost clock would suggest, especially compared to its 3DMark single-thread score of 1253. This discrepancy could indicate that the Cinebench scores for the two chips were measured under different conditions, perhaps with different memory configurations or power limits. The EPYC 9654’s single-core R23 score of 14354 seems extraordinarily high for a chip with a 3.70 GHz boost clock, which suggests the benchmark might have been run with a different version of the software or under server-specific optimizations. The data does not provide a clear explanation, so readers should treat the single-core head-to-head results with caution, as they do not align with the architectural advantages of the 9600X.

FAQ

Q: Which processor has a higher boost clock?

A: The AMD Ryzen 5 9600X has a boost clock of 5.40 GHz, which is significantly higher than the AMD EPYC 9654’s boost clock of 3.70 GHz.

Q: How do the core counts compare?

A: The AMD EPYC 9654 has 96 cores and 192 threads, while the AMD Ryzen 5 9600X has 6 cores and 12 threads. The EPYC 9654 offers 16 times the cores of the 9600X.

Q: What is the difference in L3 cache size?

A: The AMD EPYC 9654 has 384 MB of shared L3 cache, while the AMD Ryzen 5 9600X has 32 MB of shared L3 cache. The EPYC 9654’s cache is 12 times larger.

Q: Which processor supports more memory channels?

A: The AMD EPYC 9654 supports twelve-channel memory with a bandwidth of 460.8 GB/s, while the AMD Ryzen 5 9600X supports dual-channel memory with a bandwidth of 89.6 GB/s.

Q: Are both processors based on the same architecture?

A: No. The AMD Ryzen 5 9600X uses the Zen 5 architecture on a 4 nm process, while the AMD EPYC 9654 uses the Zen 4 architecture on a 5 nm process.

Q: Which processor has a higher average benchmark score?

A: The AMD Ryzen 5 9600X has an average benchmark score of 29713, which is slightly higher than the AMD EPYC 9654’s average score of 29409. However, both processors have the same percentile ranking of 81 among all CPUs.

The Verdict

The data indicates a clear split in purpose. The AMD EPYC 9654 is the definitive choice for server and workstation workloads that demand massive parallel processing. Its 96-core design, 384 MB L3 cache, and 460.8 GB/s memory bandwidth make it a powerhouse for multi-threaded applications, as evidenced by its Cinebench R23 multi-core score of 101675, which is 82.8% ahead of the Ryzen 5 9600X. Anyone running virtual machines, compiling large codebases, or processing scientific simulations should look at the EPYC 9654.

The AMD Ryzen 5 9600X is the better pick for desktop users who prioritize single-threaded performance and high clock speeds. Its 5.40 GHz boost clock and 4 nm Zen 5 architecture give it an edge in gaming and everyday tasks, even if the head-to-head single-core scores suggest otherwise. The 9600X’s integrated Radeon Graphics and unlocked multiplier make it a flexible, user-friendly part for a desktop build. Its 65 W TDP is also far more manageable than the EPYC 9654’s 360 W TDP, making it suitable for standard air cooling. For a mainstream desktop, the 9600X is the logical choice; for a data center, the EPYC 9654 is the only option.

Specification Differences

| Specification | AMD Ryzen 5 9600X | AMD EPYC 9654 |

|---|---|---|

| Cores | 6 | 96 |

| Threads | 12 | 192 |

| Base Clock | 3.90 GHz | 2.40 GHz |

| Boost Clock | 5.40 GHz | 3.70 GHz |

| TDP | 65 W | 360 W |

| Socket | AMD Socket AM5 | AMD Socket SP5 |

| Architecture | Zen 5 | Zen 4 |

| Process Node | 4 nm | 5 nm |

| Transistors | 8,315 million | 78,840 million |

| Die Size | 70.6 mm² | 12x 72 mm² |

| L1 Cache | 80 KB (per core) | 64 KB (per core) |

| L2 Cache | 1 MB (per core) | 1 MB (per core) |

| L3 Cache | 32 MB (shared) | 384 MB (shared) |

| Memory Bus | Dual-channel | Twelve-channel |

| Memory Bandwidth | 89.6 GB/s | 460.8 GB/s |

| PCIe | Gen 5, 24 Lanes (CPU only) | Gen 5, 128 Lanes (CPU only) |

| Integrated Graphics | Radeon Graphics | None |

| Multiplier Unlocked | Yes | No |

| Release Date | 2024-08-07 | 2022-11-09 |