GMKtec EVO-X2 (Ryzen AI Max+ 395)

The GMKtec EVO-X2 takes the Ryzen AI Max+ 395 and its 128GB of shared memory and wraps it in a mini-PC that, for most of its life, undercut nearly everything else with the same chip. That changed in 2026: an LPDDR5X memory shortage spiked its price to around $3,400-3,650, above the Beelink and Framework it used to beat. The capacity is still superb; the value crown has slipped, and it now depends on catching a GMKtec sale.

The take

This used to be the value pick of the 128GB boxes, plain and simple - same Strix Halo chip as the Beelink, same 128GB you can hand mostly to the graphics side, and it routinely sold for around half what the premium rivals asked. The 2026 memory shortage flipped that: the EVO-X2’s 128GB SKU jumped to around $3,400-3,650 while the Beelink held near $1,999, so today it’s the dearer of the two, not the cheaper. It still won’t win a speed contest - the memory tops out near 256 GB/s in theory and lower in practice, so a dense 70B answers at a walk - and the capacity remains superb. But buy it now for capacity, and only for value if you catch one of GMKtec’s regular sales that drops it back toward its old price.

What it’ll actually run

The Radeon 8060S draws on the shared pool, so with the memory split set generously you can put most of the 128GB toward models. That means a 70B at Q4 fits with room for context, and big mixture-of-experts models are where it shines. GMKtec’s own figures on the 128GB unit have gpt-oss-120b around 19 tokens a second, a Qwen3 30B MoE near 55, and even a 235B MoE ticking over about 11 - impressive for the money. Dense models are the slow lane: a DeepSeek R1 32B lands under 10 tokens a second, so temper expectations there.

The bottleneck is bandwidth, same as every Strix Halo box. Around 256 GB/s on paper, and real-world measurements come in lower, so dense large models feel measured rather than quick. There’s a 50 TOPS NPU on board too, but no local LLM tooling makes proper use of it yet, so the GPU does the work. Software is the reassuring part: it ships with Windows 11, runs Linux happily, and the AMD stack keeps improving. You’ll want to set the memory split in the BIOS to feed the GPU, but that’s a one-time job.

Who should buy it

Buy it if capacity is the point and you catch it at a sensible price. It’s still a fine machine for loading big models at home on Windows or Linux, and at a sale price it’s back to being the value champion. At the current shortage price, though, look hard at the Beelink GTR9 Pro first, which holds the same 128GB for less right now.

Look elsewhere if you need speed or CUDA. If your models fit in 24GB a used 3090 runs them faster for less, and if you’re tied to Nvidia’s tooling none of it lives here. The EVO-X2 is still the most model you can load in a tidy little Windows box - just no longer automatically the cheapest way to do it.