Search  for anything...
GMKtec

GMKtec AI Mini PC Ryzen Al Max+ 395 (up to 5.1GHz) Mini Gaming Computers

Based on 115 reviews
Condition: New
Checking for the best price...
$3,649.99
Save $349.01 was $3,999.00

Buy Now, Pay Later

As low as / mo
  • – Up to 36-month term if approved
  • – No impact on credit to apply
  • – Instant approval decision
  • – Secure and straightforward checkout

Ready to go? Add this product to your cart and select a plan during checkout.

Payment plans are offered through our trusted finance partners Klarna, Affirm, Afterpay, Zip, Apple Pay, and Google Pay. No-credit-needed leasing options through Acima may also be available at checkout.

Learn more about financing & leasing here.

Selected Option

Free shipping on this product

FREE 30-day refund/replacement

To qualify for a full refund, items must be returned in their original, unused condition. If an item is returned in a used, damaged, or materially different state, you may be granted a partial refund.

To initiate a return, please visit our Returns Center.

View our full returns policy here.

Availability: In Stock.
Fulfilled by Amazon
Arrives Wednesday, Oct 28
Order within 8 hours and 53 minutes

Available payment plans shown during checkout

Protect Your Purchase

Easy claims online, fast replacements, no fees

Checking for protection plans...

Recently Viewed

At a glance

Condition
New
Size
128GB+2TB I EVO X2
Model
EVO-X2
Storage
2 TB
Memory
128 GB
Screen size
75 in
Weight
3.3 kg
Warranty
GMKtec offers a 1-year limited warranty for each mini PC, starting from the date of the purchase
Works with
Headphone, Keyboard, Monitor, Mouse, Speaker

Features 10

  • EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
  • AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 Zen 5 CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
  • AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
  • EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.

Description

EVO-X2 EVO-X2 EVO-T1 EVO-T2S Nucbox K15 Nucbox K13 EVO-X1 Pro Purpose: GMKtec aims to provide customers with reliable high-quality products, professional after-sales service, and become a leading brand in the Mini PC industry. About: GMKtec is a company established in 2019, focusing on the research, design, and production sales of computer hardware. We have our own R&D & manufacturing team. Our Mini PCs deliver the best powerful performance in an ultra-compact form for everyday computing tasks.

Specs 64

Brand GMKtec
Operating System OS
CPU Model Ryzen AI
CPU Speed 5.1 GHz
Cache Size 128 GB
Graphics Card Description Integrated
Graphics Coprocessor AMD Radeon 8060S Graphics 40Cores RDNA3.5
Memory Storage Capacity 2 TB

Frequently asked questions

If you place your order now, the estimated arrival date for this product is: Wednesday, Oct 28

Yes, absolutely! You may return this product for a full refund within 30 days of receiving it.

To initiate a return, please visit our Returns Center.

View our full returns policy here.

  • Klarna Financing
  • Affirm Pay in 4
  • Affirm Financing
  • Afterpay Financing
  • Zip Pay in 4
  • Financing through Apple Pay
  • Financing through Google Pay
Leasing options through Acima may also be available during checkout.

Learn more about financing & leasing here.

Similar Products

Top Amazon Reviews

Great, with caveats
Size: 128GB+2TB I EVO X2
It's a fairly decent deal for the ability to run very large models locally. I took the plunge based on another review, and although I couldn't replicate their success in Windows (version h3ll) I am able to run GPTOSS 120B and Qwen 80B Thinking models at respectable speeds on Ubuntu 25.10. I figured it would be useful to run my own models locally for VS Code agent purposes and it's working well so far. Windows just couldn't go past 64GB when loading models, no matter the configuration. After banging my head on the wall for a day or so I gave up and wiped Windows and replaced it with Ubuntu just to see if that was the issue. It basically worked out of the box and I don't have many issues at all under Linux. This is strictly a dev machine for me so I don't mind using Ubuntu in order to have the advantage of running, and tuning, models locally. It seems well built. I've only ever felt it get mildly warm, but I've not had it long now and I'm not playing games with it. It's got a sort of retro-modern sort of ugliness which I don't hate, but I really don't care about the aesthetics of tools like this so much. It's very quick and responsive in both Windows and Linux and if you need a beast for local inference, it's hard to beat at this price. Just remember you're mostly limited to 64GB VRAM for AI models in Windows. Linux seems to be able to do about 110GB reliably. ... show more
Reviewed in the United States on January 1, 2026 by Yargnad
Very nice!
Size: 128GB+2TB I EVO X2
The system is excellent. I have read other reviews that said it is noisy but I can't even hear mine. AMD ROCm is maturing just on time. I bought this to do AI training and local LLM inference and that seems to be moving along just fine. If you interested in this system and want to research it, you can look up Strix Halo and get more insight into these systems. I've seen reports where people have even clustered these machines together for more AI capabilities. Gaming is also superb on this system. The Graphics quality will easily rival most systems. I have set mine up for dual boot - Windows 11 Pro and Ubuntu 24. This is for AI purposes while maintaining the Gaming capabilities also. This system handles this very well. Also, it comes with Windows 11 Pro and is not loaded with a bunch of bloatware. If your into gaming or especially local AI inference or training, this system is clearly a winner. Update - I just want to add that I knocked it down a star because I do experience a USB glitch under windows. I don't know if it is the system or Windows that came installed on it but when sometimes when I plug in a USB device, my USB XBox adapter loses connectivity. I then have to reinstall it and it connects again. This happens often. ... show more
Reviewed in the United States on February 18, 2026 by Darla
Very impressive Local LLM power house
Size: 128GB+2TB I EVO X2
Solid build quality. Easy to open the case and install another NVME m.2. I added another NVME drive and installed Ubuntu 24. On Windows, I was getting about 70 toks/s on Qwen3-30b-a3b-q4_k_m using LMStudio. Under Linux + Vulkan+llama.cpp, I got 86 toks/s for the same model. You can hear the fan under load, but compared to those 300+ watt GPUs, it is nothing to be complained of. For those need info on how to build Llama.cpp with various backends, search for "strix halo toolbox". Of course the point of this Strix Halo box is to run much larger models, such as the gpt-oss-120b or qwen3-235b. I will update the review when those are tested. ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = AMD Radeon Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 0 | matrix cores: KHR_coopmat | model | size | params | backend | ngl | threads | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | --------------: | -------------------: | | qwen3moe 30B.A3B Q4_K - Medium | 17.28 GiB | 30.53 B | Vulkan | 999 | 32 | pp512 | 749.37 ± 0.97 | | qwen3moe 30B.A3B Q4_K - Medium | 17.28 GiB | 30.53 B | Vulkan | 999 | 32 | tg128 | 85.92 ± 0.33 | UPDATE: CHECK THESE ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = AMD Radeon Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 0 | matrix cores: KHR_coopmat | model | size | params | backend | ngl | threads | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | --------------: | -------------------: | | gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | Vulkan | 999 | 32 | pp512 | 447.60 ± 11.58 | | gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | Vulkan | 999 | 32 | tg128 | 50.51 ± 0.34 | ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = AMD Radeon Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 0 | matrix cores: KHR_coopmat | model | size | params | backend | ngl | threads | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | --------------: | -------------------: | | qwen3moe 235B.A22B Q3_K - Large | 103.53 GiB | 235.09 B | Vulkan | 999 | 32 | pp512 | 100.73 ± 0.46 | | qwen3moe 235B.A22B Q3_K - Large | 103.53 GiB | 235.09 B | Vulkan | 999 | 32 | tg128 | 17.98 ± 0.04 | Update: running the new zImage-Turbo using pytorch + rocm7, smooth. On RTX 3090, the same model chokes due to memory size Update: Upgrade Linux kernel to 6.18, Install the pre-release pytorch+rocm7.11, (pip install --index-url https://rocm.nightlies.amd.com/v2-staging/gfx1151/ --pre torch torchaudio torchvision). Now, zImage-Turbo generate 1024*1024 images in 30 seconds ... show more
Reviewed in the United States on October 28, 2025 by Dr. History
Great machine and excellent support
Size: 128GB+2TB I EVO X2
I bought this device about five months ago. Unfortunately, it burnt out a few weeks back. At first, I thought it would be hard to fix, but I was surprised that GMKtec offered a replacement and provided friendly support, I finally have a great working machine again! I am very satisfied and recommend them to anyone, even though the performance isn't the absolute best compared to similar models, the excellent service makes it worth it. ... show more
Reviewed in the United States on March 26, 2026 by Kenney Lu
Not worth the Price tag
Size: 128GB+2TB I EVO X2
It claims to have 128GB of RAM but it is not fully utilized by the system. It is broken up in half for system and GPU. I would prefer, when I spend this kind of money, to decide on my own how the system handles all that RAM. I did not gain much of an advantage with this "AI Ready" server than my normal webserver. ... show more
Reviewed in the United States on June 14, 2026 by Gene Hawkins
Effectively early-access hardware
Size: 128GB+2TB I EVO X2
Minor gripe: The labels on the "front" are upside down. (If you want to run thhe unit laying down, you need to lay it on one side so as to not block airflow, and the label is in the wrong direction. This is not the best solution for running AI. Other platforms are more flexible, faster, less expensive... But for what's currently available this gives a lot more bang for the buck than anything else on the market. It's good if you want to run larger models and don't want to pay twice the price. This is also (as of this review) fairly cutting edge tech, and you will have to deal with software bugs. I've already run into one silly one; Memtest won't boot off its USB stick. (I was able to get it to run off a Mint installer though.) The AMD-native AI drivers are still very alpha, and you may be able to tweak them enough to run, or not. (It'll run Vulkan fine though, if probably with a performance penalty.) Build quality is very nice; my only gripe is they hid the screws for the case cover under the rubber feet. (It seems like a lot of mini PCs like to do this.) All in all, I cannot at this time recommend it for mission critical use. Unless AMD is unable to provide future promised software, it should become better in the future. This unit is good for trying things out, seeing if it can run the models you need and how fast you need them to go, and using this to evaluate future implementation. ... show more
Reviewed in the United States on August 7, 2025 by TheSHAD0W
Meh
Size: 128GB+2TB I EVO X2
After accepting all the flaws including the horrible bios, I still had to get 2 x 5090ti for 2 sustems to cover what this hyper expensive thing can't do. Getting it to be useful took quite a bit of driver-kernel-uma hell for the money it should do more.
Reviewed in the United States on May 5, 2026 by Chill Frog
It's a beast!
Size: 128GB+2TB I EVO X2
Running LLMs locally, Windows11Pro, MSOffice365, Python
Reviewed in the United States on August 18, 2026 by JC
How it works
Checking for best price...