AMD slides claim Strix Halo can beat the RTX 4070 laptop GPU by up to 68% in modern games
But the Nvidia rival tested was constrained by the Asus ROG Flow Z13's thermal design power.

At CES, AMD unveiled its Ryzen AI 300 flagship lineup codenamed Strix Halo with a beastly configuration of 16 cores, 40 Compute Units, and 128GB of unified memory. New first-party benchmarks assert that the top-end Ryzen AI Max+ 395 - that's a mouthful - is up to 68% faster than Nvidia's RTX 4070 mobile graphics in gaming. The slides also showcase how Strix Halo holds up versus Apple's M4-series chips in productivity and even dare to mention the desktop RTX 4090.
Strix Halo is split into three dies with two CCDs offering eight cores each and a large I/O die housing the iGPU (Integrated GPU) and the NPU. The highest-end Ryzen AI Max+ 395 packs 16 cores and 32 central processor threads based on the Zen 5 architecture, accompanied by the Radeon 8060S iGPU with 40 RDNA 3.5 Compute Units. All the AI Max chips have a base TDP of 55W, and can be configured from 45W to 120W. Surrounding the chip is up to 128GB of unified memory, which can be allocated in varying pools (up to 96GB) to the iGPU alone.
With the specs out of the way, let's talk performance. The Nvidia comparison system is the Asus ROG Flow Z13 with the i9-13900H and the RTX 4070 mobile (65W TGP). Across a suite of 17 games at 1080p high settings, Strix Halo handily bests its Nvidia equivalent, with an up to 68% lead in Borderlands 3, per AMD. Being first-party benchmarks, we shouldn't take them at face value. It is also prudent to mention that the RTX 4070 mobile can be configured up to 115W, but a 65W variant features in this comparison, due to the Asus ROG Flow Z13 design.
In productivity tests, Blender sees the 395+ blaze past the Core Ultra 9 288V (Lunar Lake) by 302% but that isn't an apples-to-apples comparison since the latter is a 17/30W chip. Versus Apple's M4 Pro, AMD touts an 86% lead in V-Ray, dropping to 12% in Cinebench R24. Moving over to AI performance, the XDNA 2 NPU enables the Ryzen AI MAX series to dish out 50 TOPS of AI performance, exceeding the Lunar Lake and Snapdragon X Elite series by two TOPS. AMD also claims its Strix Halo APUs can deliver 2.2x more tokens per second than the RTX 4090 when running the Llama 70B LLM (Large Language Model) at 1/6th the TDP (75W).
We highly suggest you wait for independent testing before jumping the gun, like perhaps pre-ordering a Strix Halo device. These laptops are likely to target enthusiasts as suitable alternatives to dedicated GPU options. With Strix Point laptops still costing over $1,000, pricing will play a key role in determining if Strix Halo can displace dedicated mid-ranged laptop GPUs like the RTX 4070 can be found in.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Hassam Nasir is a die-hard hardware enthusiast with years of experience as a tech editor and writer, focusing on detailed CPU comparisons and general hardware news. When he’s not working, you’ll find him bending tubes for his ever-evolving custom water-loop gaming rig or benchmarking the latest CPUs and GPUs just for fun.
-
KyaraM Claiming it can beat a 4070 is a tall claim when the 4070 in question is only allowed to draw 65W... at that wattage, the card loses around 20 FPS compared to one who is allowed to draw 100W - 140W; and the 4070 can usually still be OC'd. That's a significant difference in my book. Strix Halo does look impressive, especially for an iGPU, but I wouldn't call this an apples to apples comparison if the competitor is power limited. Especially with just the first party benchmarks that will make it look as good as possible.Reply -
Peksha It's a shame that the best 4090/5090 GPUs for AI only deliver 2.5 t/s on simple models like the Llama 3.x-70b.Reply
It's sad that they still get 4.5 stars and best choice for doing local LLMs at such an ugly speed. -
Notton The 2025 model Z13 flow is supposed to use the ryzen 395, with the same power and thermal constraints.Reply
But seeing as they don't bother mentioning what the 395 is in, I'm going to assume it's on an open air test bench. -
Peksha
RTX 4070 mobile << RTX 4060 desktop, 128b gddr6, 1.7GHz boost. It doesn't take much to beat this weak GPU. And no amount of power limits will help it, especially when compared in the same 13" chassis ;)KyaraM said:Claiming it can beat a 4070 -
oofdragon AMD would sell massive amounts of this iGPU if it was a desktop product, what are they thinking??Reply -
qwertymac93 I'm not surprised it can beat a 4090 on llama 3_70b, that model is way too big to fit into 24GB of memory and is thus extremely limited on the 4090. You need at least a pair of 3090/4090 to have a chance of fitting that model in memory, and even then you'd need quantization. Not exactly fair without context but it is true that a Strix halo with 128GB of ram would run 70b much better than a single 4090. 24GB cards are limited to about 34b with quantization for optimal performance.Reply -
ezst036 Admin said:But the Nvidia rival tested was constrained by the Asus ROG Flow Z13's thermal design power.
Were the thermals necessary due to being super thin and light?
Any GPU is going to struggle if it has far, far inadequate cooling. This whole story says probably more about the thin and light laptop than it does the superior performance of the AMD chip. It is a nice chip though. Wish I could get one in a socket on a desktop. -
jlake3
1. It almost certainly will come to mini-PCs in time. It’s not even out yet.oofdragon said:AMD would sell massive amounts of this iGPU if it was a desktop product, what are they thinking??
2. It has quad-channel unified memory, and thus cannot be a drop-in option for AM5 based desktops.
3. It’s equal to a 4070 laptop with a 65w TGP, but that configuration is easily surpassed in gaming by midrange desktop dGPUs.
4. The complexity and large iGPU and extremely fast unified RAM and the fact it can’t drop into AM5 means it would likely be very expensive for a desktop APU, and desktops needing good graphics performance but not willing to use a dGPU and being willing to pay a premium for that is a slim niche, so it’s not AMD’s launch priority. Someone will fill it eventually and people will probably complain it’s a poor value. -
Notton HP's mini-PC offering: https://www.hp.com/us-en/workstations/z2-mini-a.htmlGMK announced a mini-PC, but no product pictures yet.Reply