- AMD has published official benchmarks to Ryzen AI MAX+ 395 APU
- It demonstrates a clear lead over Intel Core Ultra 7 258V
- The tests were performed in LM Studio with different LLMs
Official benchmarks have backed up the “Strix Halo” AMD Ryzen AI Max+ 395’s performance as the “most powerful X86 APU” on the market for AI -computing.
AMD RYZEN AI MAX+ 395 is a 16-core (32 threads) processor with a 50+ top AI-tops XDNA 2 NPU and RADEON 8060S Integrated graphics (40 RDNA 3.5 Compute devices) for a serious treatment effect for the form factor. It is primarily marketed by AMD for its handling of AI workloads, such as in applications such as LM Studio.
This is evident in AMDS published benchmarks for Ryzen AI MAX+ 395, which is measured in ‘tokens per day. Second ‘and’ Time for first token ‘in LM Studio against its competition. Specifically, we see how the new “Strix Halo” processor inside the ASUS ROG Flow Z13 with 64 GB RAM is compared to a similar spec asus Zenbook S14 with 32 GB RAM.
The latter machine has half of the total memory and uses Intel Core Ultra 7 258V APU with its baked-in-arch integrated graphics clock to 140V, so it is not necessarily a comparison of 1: 1. Second with Deepseek R1, Phi 4 Mini Instruction and Llama 3.2 compared to its rival.
The cord becomes more dramatic when compared to time with the first token in text models, with up to 12.2x faster, as shown in benchmarks in Deepseek R1 Distill Qwen 14B, with a similar lead of 11.3x in Phi 4 14b. However, it is not a consistent lead across all text models as Ryzen AI Max+ 395 is everywhere from 4x to 9x faster in Llama 3.2 and other Deepseek R1 distilled models.
AMDS RYZEN AI MAX+ 395 is also claimed to be up to seven times faster in Sota Vision models in time for first token, this can be seen in IBM Granite Vision 3.2 2B, while the chip is six times faster in Google Gemma 3 12b; However, it is roughly when compared to the Gema 3 4b.
Powerful achievement that shouldn’t be too shocking
AMD’s leading “Strix Point” APU is head and shoulders over the Intel Core Ultra 7 processor in a way that should not be surprising to those interested in AI -computing. This is because Team Blue’s hardware was made with lower threshold AI -computing in mind, and this can be seen in the architectural differences when analyzing the two.
Intel Core Ultra 7 258V has eight cores and eight threads with a maximum boost -watch of up to 4.8 GHz and a maximum TDP of 37W. In contrast, AMD Ryzen AI Max+ 395 has 16 cores, 32 threads, a boost -watch of up to 5.1 GHz and a standard TDP of 55W. However, this TDP is configurable up to 120W, so it’s a night and day hardware difference in the chipsets. Of course, AMDS hardware would come out on top; It is far more powerful everywhere.
Then we have to consider the two tested machines used for benchmarks, the differences between the ASUS ROG Flow Z13 (a leading game -bearable computer) and the ASUS Zenbook S14 (an intermediate ultrabook). We reviewed the latter unit late last year and gave it a four-star write-up with reference to “Solid Performance” from the Lunar Lake processor. Chip debuted inside this machine (and the like) back in September 2024, while AMD Ryzen ™ AI MAX+ 395 hit the stage this month.
It is not only AI -Bearing computers that use the flagship Ryzen AI chipset for its performance features, as a myriad of Mini -PCs use them for productivity and even gaming use. It has become a race to launch the most powerful AI-mini PCs that are possible, as mid-March to mid-May is targeted from companies, such as GMKTEC and Aoostar, which lead the charge.
