Saturday, May 31st 2025
8-Core AMD Ryzen AI Max Pro 385 Benchmark Appears As Cheaper Strix Halo APU Launch Nears
It looks as though AMD might be planning to finally commercialize the more affordable version of its Ryzen AI Max APUs that have proven to be capable of powering impressively high-end gaming experiences. The first set of benchmarks of the new Strix Halo APU, dubbed the AMD Ryzen AI Max 385, have appeared on Geekbench, and the new APU is putting up some impressive numbers. AMD originally said that the Strix Halo line-up would be available between Q1 and Q2 2025, so the timing makes sense.
One major difference between the Ryzen AI Max 395 and the 385 is the iGPU, which is downgraded from the Radeon 8060S to the 8050S. When AMD launched the Strix Halo line-up, it revealed that AI Max Pro 385 would have an eight-core CPU paired with 32 graphics cores, instead of the 16-core CPU and 40-core iGPU setup. While we don't yet have GPU benchmark results for the 8050S, the CPU results put up by the APU are impressive on their own, with 2,489 points in the single-core benchmark and 14,136 points in the multicore benchmark. The laptop the new Ryzen silicon was tested in was an HP ZBook Ultra G1a with 32 GB of RAM. The results put the 385 only slightly behind the AI Max+ 395 in certain configurations, but in a similar HP ZBook Ultra G1a laptop, the Ryzen AI Max+ 395 comes out ahead of the 385 by as much as 45%. It's unclear just how much laptops with this new Ryzen AI Max Pro 385 APU will cost, but they will almost certainly be cheaper than the current crop of Ryzen AI Max+ laptops, which generally run well north of $2,000.
Sources:
Geekbench, WCCFTech
One major difference between the Ryzen AI Max 395 and the 385 is the iGPU, which is downgraded from the Radeon 8060S to the 8050S. When AMD launched the Strix Halo line-up, it revealed that AI Max Pro 385 would have an eight-core CPU paired with 32 graphics cores, instead of the 16-core CPU and 40-core iGPU setup. While we don't yet have GPU benchmark results for the 8050S, the CPU results put up by the APU are impressive on their own, with 2,489 points in the single-core benchmark and 14,136 points in the multicore benchmark. The laptop the new Ryzen silicon was tested in was an HP ZBook Ultra G1a with 32 GB of RAM. The results put the 385 only slightly behind the AI Max+ 395 in certain configurations, but in a similar HP ZBook Ultra G1a laptop, the Ryzen AI Max+ 395 comes out ahead of the 385 by as much as 45%. It's unclear just how much laptops with this new Ryzen AI Max Pro 385 APU will cost, but they will almost certainly be cheaper than the current crop of Ryzen AI Max+ laptops, which generally run well north of $2,000.
70 Comments on 8-Core AMD Ryzen AI Max Pro 385 Benchmark Appears As Cheaper Strix Halo APU Launch Nears
Can I use copilots offline with the help of NPU?
Cards would get bigger, heavier, slower, more expensive.
You can use Copilot locally with NPU.
Also those are mostly laptops chip, not desktop chips, sure they've been repurposed as small desktop in some cases, but they've been engineered to be an efficient platform for laptops.
Currently the NPUs are still facing the fragmentation scenario, even though DirectML is right there, so it's hard for a developer to be able to integrate such features without knowing the specifics of each vendor and implementing all different SDKs out there instead of a common API.Wait, can you? The actual MS Copilot stuff? Do you have any source on that?
So far all I've heard is that they're planning on that, but haven't deployed it yet.
Example:
www.pcworld.com/article/2569111/microsoft-wants-to-run-copilot-locally-on-your-pc-starting-early-2025.html
They do have models like their Phi series out for quite some time, but I haven't seen it being used within the OS yet, only through 3rd party stuff such as LM Studio and whatnot.
If they add another 8CUs on RDNA4 or UDNA, with 24 big CPU cores, it will be a beastly APU anyway. AMD does things incrementally. They know they need to add more IO next time as iGPU is already very good. They need to have on Medusa Halo as many PCIe lanes as they have on AM5 chips, plus integrated USB4 v2 at 80 Gbps. XDNA3 will be bigger too, as well as wider DRAM bus. So, that's a lot of stuff to fit in.
Strix Halo is primarily a vehicle for mobile platforms right now, and for testing new Infinity Fabric for Zen6 adoption. They are clearly going for some users of Apple devices with similar system, but on x86. They could hit a jackpot with it in future if they manage to offer a variant of it for DIY users on a mainstream socket.
Also that is gonna be a $1500+ APU at that point. Not to mention that if they can shrink the GPU cores small enough to make sense on an APU, the dGPUs will also benefit and 64 will be the new 40. Same way everyone predicted that APUs would dominate at 1080p after Llano released and 10 years later the current strix point cant consistently manage 1080p across the board.To really feed a proper big APU with DDR5 you would need a 4000+ pin server socket that supports 8 lanes of DDR5. Even then bandwidth would be an issue.
The EPYC genoa lineup supports 12 DDR5 channels, for up to 480GB/s of bandwidth. The RX 9070xt has a 640+GB/s memory bus just for itself.
It could see more widespread usage if CAMM2 ever gets out of the goofing off stage and become a viable memory system, since each CAMM2 is 128 bit on its own and 4 of them would be a lot easier to fit then 8 DDR5 modules and they hypothetically can hit DDR5x speed.
newest(ups next year)server DDR5 12800... Please make math for me what will be bandwidth with 16 channel DDR5 12800! ;)Strix Halo's unified memory advantage here is just about the same of the Apple M-series chips, it's not nearly as much about the raw bandwidth or compute power as it is about the capacity attainable, and large LLMs love capacity, which takes precedence over BW and compute power both - a 5090 or R9700 will run a model that fits under 32 GB faster than pretty much anything else in and around their price ranges, as they've got both the performance and the bandwidth, but they won't run a model that an SoC with 128 GB of unified memory can run nearly as well as they otherwise should. If you want that out of a traditional GPU, prepare your wallet for a RTX Pro 6000, pricing starts at a nice 5 digits.
I believe Venice would support 7200MT/s at best.
Nonetheless, the math for memory bandwidth is # of channels * bits per channel * frequency / 8. So for 16c DDR5 12800 we would have ~1.6TB/s.
Using a more realistic 6400MHz scenario, it'd be close to 820GB/s.Venice is supposed to be a 2026 product, so I doubt it'll have MRDIMM support to begin with.
9600 MT/s CKD sticks should be much more prevalent and easy to obtain at this point in time if they were on-track to achieve that, especially at those densities, but best we can do right now is a nearly perma out-of-stock, $500, 2x24 kit that pretty much requires the Z890 Apex and a lucky 285K processor to break the 10000 MT/s ceiling :(
Personally I highly doubt we will ever see anything close to that on DDR5. We cant even get 9500 to consistently run stable in soldered LPDDR5X form, to hit higher then that on standard SODIMMs? I dont think so.