AMD Ryzen 7 170 vs Intel Core Ultra 5 336H Comparison

The Verdict

The recorded data splits these two mobile processors along sharp performance lines. The Intel Core Ultra 5 336H wins 10 of the 11 head-to-head benchmark comparisons, including every major multithreaded and single-threaded workload except integer math. The AMD Ryzen 7 170 takes only a single win, but that win is substantial. For users whose work involves heavy integer arithmetic, the AMD part is clearly the stronger choice. For nearly everything else measured, the Intel part delivers higher scores, often by wide margins. The Intel chip also posts a higher PassMark multithread score (28545 versus 20760) and a higher single-thread score (4013 versus 3128). Notably, the AMD chip holds a higher overall percentile ranking (88th versus 84th) despite losing most direct comparisons, which indicates its average score across all database entries benefits from a different benchmark mix. The AMD part also has a higher average benchmark score of 43689 compared to 34485 for Intel. In practical terms, the Intel Core Ultra 5 336H is the default pick for general compute, encoding, physics simulation, and encryption tasks, while the AMD Ryzen 7 170 is the specialist for integer-heavy code.

Architecture Differences

The two processors come from different design philosophies. The AMD Ryzen 7 170 uses the Zen 3+ architecture on a 6 nm TSMC process, with a Rembrandt-R codename and an AMD Socket FP7. It has 8 cores and 16 threads, which means each core supports two threads. The Intel Core Ultra 5 336H uses the Panther Lake architecture on a 3 nm Intel process, with an Intel BGA 2540 socket. It has 16 cores and 16 threads, meaning every core is single-threaded. This core count difference explains why the Intel part leads in parallel workloads: it has twice as many physical cores, even though thread counts match at 16. The AMD chip features a 16 MB shared L3 cache, while the Intel chip has an 18 MB shared L3 cache. Per-core cache also differs: AMD provides 64 KB of L1 and 512 KB of L2 per core, while Intel provides 192 KB of L1 and 2.5 MB of L2 per core. The Intel part supports DDR5 and LPDDR5X memory, while the AMD part supports DDR5 only. Both use dual-channel memory buses, but the Intel chip shows a higher memory bandwidth of 115.2 GB/s versus 76.8 GB/s for AMD. The AMD chip supports ECC memory; the Intel chip does not. PCIe connectivity also differs: AMD has Gen 4 with 20 lanes, Intel has Gen 5 with 12 lanes. Integrated graphics differ as well: AMD uses Radeon 680M, Intel uses Intel Xe3 Graphics. The Intel part has a lower TDP of 25 watts compared to 35 watts for AMD, yet it still produces higher scores in most tests.

Head-to-Head Benchmarks

The Intel Core Ultra 5 336H dominates the head-to-head results. The largest margin comes in the find prime numbers test, where Intel scores 299 versus AMD's 49, a delta of -83.6% from the AMD perspective. That is a massive gap, indicating the Intel architecture handles this specific primality workload far more efficiently. Physics simulation also shows a huge Intel advantage: 2682 versus 890, a -66.8% delta. Floating point math follows with Intel at 82415 versus AMD at 44979, a -45.4% delta. Data encryption shows Intel at 21291 versus AMD at 16078, a -24.5% delta. Extended instructions see Intel at 24542 versus AMD at 18107, a -26.2% delta. The multithread test gives Intel 28545 versus AMD 20760, a -27.3% delta. Single-thread performance shows Intel at 4013 versus AMD at 3128, a -22.1% delta. Random string sorting favors Intel at 34402 versus 27804, a -19.2% delta. Data compression is closer but still Intel: 280340 versus 265920, a -5.1% delta. The sole AMD win comes in integer math, where AMD scores 79738 versus Intel's 62070, a +28.5% delta for AMD. This single result shows that AMD's Zen 3+ cores retain a clear edge in pure integer arithmetic, even though the Intel chip wins in every other measured category. The database also includes Cinebench results only for the Intel part: R15 multicore 2418, R15 singlecore 341, R20 multicore 10076, R20 singlecore 1422, R23 multicore 23991, and R23 singlecore 3387. No comparable Cinebench scores exist for the AMD chip in the database, so a direct Cinebench comparison is not possible from recorded data.

Specification Differences

The two processors differ in several key specification fields. Core count: AMD has 8, Intel has 16. Thread count: both have 16, but AMD achieves this via SMT while Intel uses one thread per core. Base clock: AMD runs at 3.20 GHz, Intel at 1.90 GHz. Boost clock: AMD at 4.75 GHz, Intel at 4.60 GHz. TDP: AMD at 35 watts, Intel at 25 watts. Process node: AMD on 6 nm TSMC, Intel on 3 nm Intel. L1 cache per core: AMD 64 KB, Intel 192 KB. L2 cache per core: AMD 512 KB, Intel 2.5 MB. L3 cache shared: AMD 16 MB, Intel 18 MB. Memory support: AMD DDR5, Intel DDR5 and LPDDR5X. Memory bandwidth: AMD 76.8 GB/s, Intel 115.2 GB/s. ECC support: AMD yes, Intel no. PCIe: AMD Gen 4 with 20 lanes, Intel Gen 5 with 12 lanes. Integrated graphics: AMD Radeon 680M, Intel Xe3 Graphics. Socket: AMD Socket FP7, Intel BGA 2540. Release date: AMD 2025-09-30, Intel 2026-01-04. Both are mobile segments, both are active production, both have locked multipliers. The AMD part has a part number of 100-000000989, the Intel part has SA4RD. Neither has a recorded launch MSRP in the database.

FAQ

Q: Which processor has more cores?

A: The Intel Core Ultra 5 336H has 16 cores, while the AMD Ryzen 7 170 has 8 cores. Both have 16 threads, but Intel achieves this with 16 single-threaded cores, while AMD uses 8 cores with two threads each.

Q: Which processor wins the multithread benchmark?

A: The Intel Core Ultra 5 336H wins the PassMark multithread test with a score of 28545, compared to 20760 for the AMD Ryzen 7 170, a delta of -27.3% from AMD's perspective.

Q: Does the AMD processor win any benchmark?

A: Yes. The AMD Ryzen 7 170 wins the integer math test with a score of 79738, versus 62070 for the Intel Core Ultra 5 336H, a +28.5% delta for AMD. This is the only head-to-head win for AMD out of 11 tests.

Q: Which processor has higher memory bandwidth?

A: The Intel Core Ultra 5 336H has a memory bandwidth of 115.2 GB/s, while the AMD Ryzen 7 170 has 76.8 GB/s. Intel also supports LPDDR5X memory in addition to DDR5, while AMD supports DDR5 only.

Q: What is the TDP difference?

A: The AMD Ryzen 7 170 has a TDP of 35 watts, while the Intel Core Ultra 5 336H has a TDP of 25 watts. The Intel part has a lower TDP yet delivers higher scores in most benchmarks.

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

A: The Intel Core Ultra 5 336H has a single-thread score of 4013, compared to 3128 for the AMD Ryzen 7 170, a -22.1% delta from AMD's perspective.

Where Each One Wins

The Intel Core Ultra 5 336H wins in data compression, data encryption, extended instructions, find prime numbers, floating point math, multithread, physics, random string sorting, and single-thread tests. These are broad categories covering encryption, scientific floating-point work, compression, sorting, and physics simulation. The Intel chip also shows a lower TDP (25 versus 35 watts) and higher memory bandwidth (115.2 GB/s versus 76.8 GB/s), which supports its strong parallel performance. The AMD Ryzen 7 170 wins only in integer math, but that win is decisive (79738 versus 62070). The AMD chip also has a higher average benchmark score (43689 versus 34485) and a higher percentile ranking (88th versus 84th), suggesting that in the broader database context, the AMD part holds up well against other CPUs even if it loses to this specific Intel rival. The AMD chip supports ECC memory, which the Intel part does not, and uses a different socket (FP7 versus BGA 2540). For workloads dominated by integer arithmetic, such as certain database operations or checksum calculations, the AMD Ryzen 7 170 is the measured leader. For all other recorded workloads, the Intel Core Ultra 5 336H produces higher scores, often by double-digit percentages. The data also shows the Intel part has a larger L3 cache (18 MB versus 16 MB) and larger per-core L1 and L2 caches, which likely contributes to its lead in latency-sensitive tests like single-thread and physics. The AMD part has a higher boost clock (4.75 GHz versus 4.60 GHz), which may help in its single integer win, but the Intel part's architecture and core count dominate the rest of the field.