AMD Ryzen 9 7900X vs AMD Ryzen AI Embedded P164 Comparison

AMD
AMD

AMD Ryzen 9 7900X

CORE STATE Raphael
CORE SPECS 12 Cores / 24 Threads
CLOCK SPEED 4.7 Base / 5.6 GHz Turbo
CACHE 64 MB (shared)
MAX TDP 170W
ARCHITECTURE Zen 4
nm
PROCESS 5 nm
LAUNCH DATE 2022
VS
AMD
AMD

Ryzen AI Embedded P164

CORE STATE Gorgon Point
CORE SPECS 8 Cores / 16 Threads
CLOCK SPEED 2 Base / 5 GHz Turbo
CACHE 8 MB
MAX TDP 28W
ARCHITECTURE Gorgon Point
nm
PROCESS 4 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_16_threads
10,972
N/A
3dmark_2_threads
2,137
N/A
3dmark_4_threads
4,151
N/A
3dmark_8_threads
7,798
N/A
3dmark_max_threads
12,536
N/A
3dmark_single_thread
1,093
N/A
cinebench_cinebench_r15_multicore
4,820.5
N/A
cinebench_cinebench_r15_singlecore
323
N/A
cinebench_cinebench_r23_multicore
29,300
N/A
cinebench_cinebench_r23_singlecore
2,016.5
N/A
geekbench_multicore
19,267
N/A
geekbench_singlecore
2,617
N/A
passmark_data_compression
632,505
327,891
passmark_data_encryption
37,263
16,055
passmark_extended_instructions
47,619
24,193
passmark_find_prime_numbers
388
71
passmark_floating_point_math
103,952
55,799
passmark_integer_math
169,273
87,940
passmark_multithread
51,406
25,889
passmark_physics
3,060
1,210
passmark_random_string_sorting
74,658
34,801
passmark_single_thread
4,238
4,029
passmark_singlethread
4,238
4,029

Analysis: AMD Ryzen 9 7900X vs AMD Ryzen AI Embedded P164

The AMD Ryzen 9 7900X and the AMD Ryzen AI Embedded P164 occupy very different corners of the processor market, yet they land within 0.7% of each other in average benchmark score. The desktop-focused 7900X, a 12-core Zen 4 part, squares off against an 8-core Zen 5 / Zen 5c embedded mobile chip. While the P164 posts a respectable average score of 52901, the 7900X edges it out with 53288, but the real story lies in the scale of the performance gaps across individual workloads.

Head-to-Head Benchmarks

The Ryzen 9 7900X wins all 11 head-to-head benchmark comparisons against the Ryzen AI Embedded P164, but the margins tell a nuanced story. The largest victory comes in the PassMark find prime numbers test, where the 7900X scores 388 versus the P164’s 71, a staggering 446.5% advantage. This extreme delta highlights the 7900X’s superior raw integer throughput per thread, as the desktop chip’s higher base clock of 4.70 GHz and boost clock of 5.60 GHz dwarf the embedded part’s 2.00 GHz base and 5.00 GHz boost.

The multithreaded workloads show a consistent pattern of roughly doubling performance. In PassMark multithread, the 7900X scores 51406 against 25889, a 98.6% lead. Data encryption follows a similar trajectory, with the 7900X posting 37263 versus 16055, a 132.1% advantage. The physics test shows a 152.9% gap, with scores of 3060 and 1210 respectively. These results align with the core count disparity: the 7900X brings 12 cores and 24 threads, while the P164 halves that to 8 cores and 16 threads.

Not every benchmark shows such dramatic separation. The single-threaded PassMark tests reveal a much tighter contest, with the 7900X scoring 4238 against the P164’s 4029, a modest 5.2% lead. This narrow margin suggests that the Zen 5 architecture in the P164, despite lower clocks, closes much of the per-core gap against the older Zen 4 design. The 7900X’s 4.70 GHz base clock likely carries it over the finish line, but the embedded chip’s newer microarchitecture keeps the fight close.

Intermediate workloads land between these extremes. Floating point math shows an 86.3% gap, with scores of 103952 and 55799. Integer math follows at 92.5%, with 169273 versus 87940. Data compression shows a 92.9% advantage for the 7900X, scoring 632505 against 327891. Extended instructions, a test of SIMD and vector processing, gives the 7900X a 96.8% lead, with 47619 versus 24193. Random string sorting rounds out the list with a 114.5% advantage, scoring 74658 against 34801.

Where Each One Wins

The Ryzen 9 7900X is the clear winner for desktop productivity and content creation workloads. Its 12-core, 24-thread configuration with a 64 MB shared L3 cache provides substantial headroom for heavily threaded applications like video encoding, 3D rendering, and software compilation. The 3DMark results reinforce this, with the 7900X scoring 12536 in max-thread tests and 10972 in 16-thread tests, while the P164 has no corresponding 3DMark entries in the data. The 7900X also leads in single-thread performance, scoring 4238 in PassMark single-thread versus 4029, making it the better choice for lightly threaded tasks that still demand fast response times.

The Ryzen AI Embedded P164, despite losing every direct comparison, wins on platform efficiency and integration. Its 28 W TDP is a fraction of the 7900X’s 170 W, making it suitable for fanless or passively cooled embedded systems where power draw is a primary constraint. The P164’s 4 nm process node, compared to the 7900X’s 5 nm, indicates a more modern manufacturing process that enables lower power consumption at comparable per-core performance. The embedded chip also supports LPDDR5X memory alongside DDR5, offering flexibility for compact, power-sensitive designs.

The P164’s integrated Radeon 880M graphics provides a more capable iGPU than the 7900X’s base Radeon Graphics, which may matter for embedded visual workloads or digital signage. The 7900X, however, offers PCIe Gen 5 with 24 lanes, doubling the bandwidth potential of the P164’s PCIe Gen 4 with 16 lanes. For systems requiring high-speed storage or GPU connectivity, the 7900X is superior, but the P164’s lower power envelope and embedded focus make it the logical pick for industrial, edge, or mobile-adjacent applications.

Architecture Differences

The two processors represent distinct architectural generations. The Ryzen 9 7900X uses Zen 4, codenamed Raphael, built on TSMC’s 5 nm process. It packs 13,140 million transistors across a dual-die design measuring 2x 71 mm². This chip features 12 cores and 24 threads, with 64 KB of L1 cache per core, 1 MB of L2 per core, and a substantial 64 MB of shared L3 cache. The 7900X runs on AMD Socket AM5 and supports DDR5 memory in a dual-channel configuration, delivering 83.2 GB/s of bandwidth. It also supports ECC memory and has an unlocked multiplier for overclocking.

The Ryzen AI Embedded P164, codenamed Gorgon Point, uses a hybrid Zen 5 / Zen 5c architecture on TSMC’s 4 nm node. The die size is significantly larger at 233 mm², though transistor count is not listed. It provides 8 cores and 16 threads, with a larger 80 KB L1 cache per core but only 1 MB of L2 per core and a modest 8 MB of L3 cache. The P164 uses AMD Socket FP8, a mobile/embedded socket, and supports both DDR5 and LPDDR5X memory. Its memory bandwidth is slightly higher at 89.6 GB/s, though it operates over a dual-channel bus. ECC memory support is present, but the multiplier is locked, preventing overclocking.

The cache hierarchy presents a significant contrast. The 7900X’s 64 MB L3 cache is eight times larger than the P164’s 8 MB. This massive L3 allocation benefits workloads with large working sets, such as databases or scientific simulations, by reducing memory latency. The P164’s smaller cache, coupled with lower clocks, explains its substantial deficit in multithreaded benchmarks despite the newer architecture.

The memory and I/O capabilities also diverge. The 7900X offers PCIe Gen 5 with 24 CPU lanes, while the P164 provides PCIe Gen 4 with 16 lanes. The 7900X’s launch MSRP is $549, a figure that reflects its desktop performance positioning. The P164 has no listed launch MSRP, consistent with its embedded market role where pricing is negotiated per contract. The 7900X was released on 2022-09-26, while the P164 is slated for 2026-03-08, indicating the embedded chip is a future-generation product.

FAQ

Q: Which processor has a higher single-thread performance?

A: The Ryzen 9 7900X leads in PassMark single-thread with a score of 4238 versus the Ryzen AI Embedded P164’s 4029, a 5.2% advantage. The 7900X’s higher boost clock of 5.60 GHz likely contributes to this edge despite the P164’s newer Zen 5 architecture.

Q: How large is the multithreaded performance gap?

A: In PassMark multithread, the 7900X scores 51406 against the P164’s 25889, a 98.6% lead. This near-doubling of performance stems from the 7900X’s 12 cores and 24 threads versus the P164’s 8 cores and 16 threads.

Q: Does the Ryzen AI Embedded P164 support ECC memory?

A: Yes, the P164 supports ECC memory, as does the Ryzen 9 7900X. Both processors also run dual-channel memory, though the P164 supports LPDDR5X in addition to DDR5, while the 7900X supports only DDR5.

Q: Which processor has more cache?

A: The Ryzen 9 7900X has 64 MB of shared L3 cache, which is eight times larger than the 8 MB L3 cache on the Ryzen AI Embedded P164. The 7900X also has 64 KB of L1 per core versus the P164’s 80 KB per core, but the P164 matches the 1 MB L2 per core.

Q: What is the power consumption difference?

A: The Ryzen 9 7900X has a TDP of 170 W, while the Ryzen AI Embedded P164 has a TDP of just 28 W. This 142 W difference makes the P164 dramatically more power-efficient for embedded or mobile applications.

Q: Can the Ryzen AI Embedded P164 be overclocked?

A: No, the P164 has a locked multiplier, preventing overclocking. The Ryzen 9 7900X, in contrast, has an unlocked multiplier, allowing users to push performance beyond stock settings.

The Verdict

The data paints a clear picture: the Ryzen 9 7900X is the superior performer across every measured benchmark, with wins ranging from 5.2% in single-thread to 446.5% in prime number computation. For users building a desktop workstation or gaming rig where raw performance is paramount, the 7900X is the definitive choice. Its 12-core, 24-thread layout, 64 MB L3 cache, and 5.60 GHz boost clock deliver benchmark results that consistently double or nearly double the P164’s scores in multithreaded tasks. The 170 W TDP is a trade-off, but for an AM5 desktop platform, it is a manageable one.

The Ryzen AI Embedded P164, despite losing every head-to-head comparison, serves a fundamentally different purpose. Its 28 W TDP, support for LPDDR5X memory, and 4 nm process make it ideal for embedded systems, industrial PCs, or fanless designs where power efficiency outweighs raw throughput. The 8-core Zen 5 configuration still achieves a 91st percentile ranking among all CPUs, and its single-thread performance trails the 7900X by only 5.2%, demonstrating that the newer architecture narrows the per-core gap. For applications that prioritize compactness, low heat output, and modern integration over maximum compute, the P164 is the appropriate selection. The data shows two competent processors, but they serve mutually exclusive markets: one for peak performance, the other for efficient, space-constrained deployment.

DETAILED SPECIFICATIONS

SPECIFICATION
9 7900X
AI Embedded P164
Core Specs
Cores
12
8 -33.3%
Threads
24
16 -33.3%
Base Clock (GHz)
4.7
2 -57.4%
Boost Clock (GHz)
5.6
5 -10.7%
Frequency (GHz)
4.7
2 -57.4%
Turbo Clock (GHz)
5.6
5 -10.7%
Multiplier
47
20 -57.4%
SMP CPUs
1
1 0.0%
Cache
L1 Cache
64 KB (per core)
80 KB (per core)
L2 Cache
1 MB (per core)
1 MB (per core)
L3 Cache
64 MB (shared)
8 MB
Power
TDP (W)
170
28 -83.5%
PPT
230 W
—
Configurable TDP
—
15-54 W
Architecture
Architecture
Zen 4
—
Codename
Raphael
Gorgon Point
Generation
Ryzen 9 (Zen 4 (Raphael))
Ryzen AI Embedded (Zen 5 / Zen 5c)
Process Size
5 nm
4 nm
Transistors
13,140 million
—
Die Size
2x 71 mm²
233 mm²
Foundry
TSMC
TSMC
Memory
Memory Support
DDR5
DDR5, LPDDR5X
Memory Bus
Dual-channel
Dual-channel
Memory Bandwidth
83.2 GB/s
89.6 GB/s
ECC Memory
Yes
Yes
Platform
Socket
AMD Socket AM5
AMD Socket FP8
Chipsets
X670E, X670, B650E, B650
—
PCIe
Gen 5, 24 Lanes(CPU only)
Gen 4, 16 Lanes(CPU only)
Intel Hybrid
Hybrid Cores
—
3 + 5
E-Core Frequency
—
2000 MHz up to 3.3 GHz
AMD Multi-Die
IO Process Size
6 nm
—
AI/NPU
NPU
—
Yes / 50 TOPS
Graphics
Integrated Graphics
Radeon Graphics
Radeon 880M
Other
Market
Desktop
Mobile
Production Status
Active
Active
Launch Price
$549
—
Part Number
100-000000589
unknown
Package
FC-LGA1718
FP8
Tj Max
100°C
105°C
View Ryzen 9 7900X Details View Ryzen AI Embedded P164 Details