AMD Ryzen 5 150 vs NVIDIA DGX Spark (MediaTek AHJ11488B) Comparison

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark comparisons between the AMD Ryzen 5 150 and the NVIDIA DGX Spark (MediaTek AHJ11488B). The head-to-head benchmark list is empty, and the win counts for both processors are zero. This absence of comparative test data means any performance assessment must rely on the individual benchmark results recorded for the AMD Ryzen 5 150 and the architectural specifications of the NVIDIA DGX Spark.

For the AMD Ryzen 5 150, the recorded PassMark scores provide a detailed picture of its performance. The multi-thread score is 17492, while the single-thread score is 3155. Integer math performance is recorded at 62151, floating-point math at 35118, and extended instructions at 14675. Data compression scores 211289, data encryption scores 13425, and random string sorting scores 22382. Physics score is 806, and the find prime numbers test scores 47. The average benchmark score is 34881, placing the processor in the 84th percentile of all CPUs in the database.

The NVIDIA DGX Spark has no recorded benchmark scores. Its average benchmark score is listed as 0, and it sits in the 50th percentile of all CPUs, though that percentile is based on specifications rather than measured performance. The absence of test data for the DGX Spark means no direct numerical comparison can be made. The nearest rivals for the AMD Ryzen 5 150 include the Intel Xeon 6349P with an average score of 34890 and a delta of 0 percent, the Intel Core 7 253PTE at 34962 with a delta of -0.2 percent, the Intel Core i7-13800H at 34988 with a delta of -0.3 percent, and the Intel Core i9-12900HX at 35003 with a delta of -0.3 percent. These deltas indicate the Ryzen 5 150 is essentially level with those processors, within 0.3 percent of their average scores.

FAQ

Q: Which processor has more cores?

A: The NVIDIA DGX Spark has 20 cores, while the AMD Ryzen 5 150 has 6 cores. The DGX Spark also uses 20 threads, one per core, whereas the Ryzen 5 150 supports 12 threads from its 6 cores.

Q: What are the clock speed differences?

A: The AMD Ryzen 5 150 has a base clock of 3.30 GHz and a boost clock of 4.55 GHz. The NVIDIA DGX Spark has a base clock of 2.80 GHz and a boost clock of 4.00 GHz. The Ryzen 5 150 holds the advantage in both base and boost frequencies.

Q: Which processor has higher memory bandwidth?

A: The NVIDIA DGX Spark offers 273.1 GB/s of memory bandwidth with quad-channel LPDDR5X support. The AMD Ryzen 5 150 provides 76.8 GB/s with dual-channel DDR5 support. The DGX Spark delivers roughly 3.5 times the memory bandwidth of the Ryzen 5 150 based on these figures.

Q: What is the process node for each processor?

A: The AMD Ryzen 5 150 is built on a 6 nm process at TSMC. The NVIDIA DGX Spark uses a smaller 3 nm process, also at TSMC.

Q: Does the AMD Ryzen 5 150 have recorded benchmark scores?

A: Yes, the Ryzen 5 150 has a full set of PassMark scores, including a multi-thread score of 17492 and a single-thread score of 3155. Its average benchmark score is 34881, placing it in the 84th percentile of all CPUs.

Q: Does the NVIDIA DGX Spark have any benchmark scores in the database?

A: No, the DGX Spark has no recorded benchmark scores. Its average benchmark score is 0, and it has no nearest rivals listed in the database.

The Verdict

The data supports a clear split between these two processors, though the comparison is limited by the lack of benchmark results for the NVIDIA DGX Spark. The AMD Ryzen 5 150 is a measured quantity: its average benchmark score of 34881 places it in the 84th percentile of all CPUs, and its nearest rivals are within 0.3 percent of its score. The DGX Spark has no measured performance data, so its capabilities must be inferred from its specifications.

For workloads that depend on high core counts and memory bandwidth, the NVIDIA DGX Spark has the structural advantage. Its 20 cores, 2 MB of L2 cache per core, 8 MB of shared L3 cache, and 273.1 GB/s of memory bandwidth indicate a design aimed at parallel and memory-intensive tasks. The Ryzen 5 150, with 6 cores, 16 MB of shared L3 cache, and 76.8 GB/s of bandwidth, is a more modest configuration.

For workloads where single-thread speed and higher clock rates matter, the AMD Ryzen 5 150 appears better positioned. Its boost clock of 4.55 GHz exceeds the DGX Spark's 4.00 GHz, and its single-thread score of 3155 is the only directly measured single-thread figure available. The Ryzen 5 150 also draws less power at 35 W TDP compared to the DGX Spark's 140 W, though power efficiency is not a direct performance metric.

Specification Differences

The two processors differ across nearly every specification category. The AMD Ryzen 5 150 has 6 cores and 12 threads, while the NVIDIA DGX Spark has 20 cores and 20 threads. Base clocks are 3.30 GHz for the Ryzen 5 150 and 2.80 GHz for the DGX Spark. Boost clocks are 4.55 GHz and 4.00 GHz, respectively. TDP is 35 W for the AMD part and 140 W for the NVIDIA part. The Ryzen 5 150 uses AMD Socket FP7, while the DGX Spark has no socket listed. Process nodes are 6 nm for the AMD part and 3 nm for the NVIDIA part, both at TSMC. Die sizes are close: 210 mm² for the Ryzen 5 150 and 208 mm² for the DGX Spark. Cache configurations differ substantially. The Ryzen 5 150 has 64 KB of L1 per core, 512 KB of L2 per core, and 16 MB of shared L3. The DGX Spark has 128 KB of L1 per core, 2 MB of L2 per core, and 8 MB of shared L3. Memory support is DDR5 with a dual-channel bus for the AMD part, versus LPDDR5X with a quad-channel bus for the NVIDIA part. Memory bandwidth is 76.8 GB/s versus 273.1 GB/s. PCIe support is Gen 4 with 20 CPU lanes on the AMD part, while the DGX Spark lists PCIe as N/A. Integrated graphics are Radeon 660M on the Ryzen 5 150 and GB20B "Blackwell" on the DGX Spark. Both are classified as mobile market segment and active production status. Release dates are 2025-09-30 for the AMD part and 2025-10-14 for the NVIDIA part. The DGX Spark has a launch MSRP of $3999, while the Ryzen 5 150 has no launch MSRP listed. Neither processor has an unlocked multiplier.

Architecture Differences

The architectural designs diverge at the foundation. The AMD Ryzen 5 150 uses the Zen 3+ architecture under the Rembrandt-R codename, built on a 6 nm process. The NVIDIA DGX Spark uses the GB10 codename under the Spark (GB10) generation, built on a 3 nm process. The AMD part sets no explicit architecture field beyond the Zen 3+ designation in its generation text, while the DGX Spark's architecture field is null, though its codename and generation identify it as a GB10 design.

Core design philosophy differs sharply. The Ryzen 5 150 uses 6 cores with simultaneous multi-threading, yielding 12 threads. The DGX Spark uses 20 cores with no multi-threading, yielding 20 threads. Cache hierarchy reflects these different orientations. The Ryzen 5 150 allocates 64 KB of L1 per core and 512 KB of L2 per core, with a shared 16 MB L3 pool. The DGX Spark allocates 128 KB of L1 per core and 2 MB of L2 per core, with a smaller shared 8 MB L3 pool. The larger per-core L2 on the DGX Spark suggests a design that feeds each core with more local data, while the Ryzen 5 150 relies more heavily on its larger shared L3 cache.

Memory architecture also differs fundamentally. The Ryzen 5 150 uses dual-channel DDR5 with 76.8 GB/s bandwidth. The DGX Spark uses quad-channel LPDDR5X with 273.1 GB/s bandwidth. The DGX Spark's integrated graphics is the GB20B "Blackwell" GPU, while the Ryzen 5 150 uses the Radeon 660M. The AMD part supports PCIe Gen 4 with 20 CPU lanes; the DGX Spark lists PCIe as N/A, suggesting a different expansion or integration path. Both processors are fabricated by TSMC, but at different nodes: 6 nm for AMD and 3 nm for NVIDIA.

Where Each One Wins

The AMD Ryzen 5 150 wins on measured single-thread performance. Its single-thread score of 3155 is the only such figure in the database, and its boost clock of 4.55 GHz is the highest clock speed between the two. For applications that scale with clock frequency and per-core efficiency, the data points to the Ryzen 5 150. Its average benchmark score of 34881 and 84th percentile ranking give it a concrete performance profile that the DGX Spark cannot match with recorded numbers.

The AMD part also wins on power efficiency. Its 35 W TDP is a quarter of the DGX Spark's 140 W. For mobile systems where thermal and power budgets are constrained, that difference is substantial. The Ryzen 5 150 also offers PCIe Gen 4 with 20 lanes, which provides expansion options the DGX Spark does not list.

The NVIDIA DGX Spark wins on raw core count and memory throughput. Its 20 cores triple the Ryzen 5 150's 6 cores, and its 273.1 GB/s memory bandwidth is roughly 3.5 times the AMD part's 76.8 GB/s. For workloads that parallelize across many cores and stream large datasets, the DGX Spark's specifications are aligned with those demands. Its 2 MB of L2 per core, quadruple the Ryzen 5 150's 512 KB per core, also points to strong per-core data locality. The DGX Spark's 3 nm process node is two generations ahead of the 6 nm node used by the Ryzen 5 150 in terms of lithography size, though process advantages do not translate directly into benchmark wins.

The DGX Spark's 8 MB of shared L3 is half the Ryzen 5 150's 16 MB, so in cache-heavy workloads that favor a large shared pool, the AMD part has the structural edge. The Radeon 660M integrated graphics on the Ryzen 5 150 and the GB20B "Blackwell" on the DGX Spark represent two different graphics approaches, but without benchmark data on either, no quantitative comparison is possible.

The release dates are close: the Ryzen 5 150 launched on 2025-09-30 and the DGX Spark on 2025-10-14. Both are listed as active production and target the mobile market segment. The DGX Spark carries a launch MSRP of $3999; the Ryzen 5 150 has no listed launch MSRP. Neither has an unlocked multiplier.

In practical terms, the Ryzen 5 150 is the processor with measured results, a strong percentile ranking, and lower power draw. The DGX Spark is the processor with the larger core count, higher memory bandwidth, and a more advanced process node, but it lacks any benchmark scores in the database to confirm how those specifications translate into real performance. The choice between them depends on whether the workload favors measured single-thread and efficiency characteristics or raw parallel throughput on paper.