---
product_id: 706886749
title: "GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe"
brand: "gmktec"
price: "11292 kr"
currency: NOK
in_stock: true
reviews_count: 13
category: "Gm Ktec"
url: https://www.desertcart.no/products/706886749-gmktec-m2-pro-s-mini-pc-intel-core-i7-1185g7
store_origin: NO
region: Norway
---

# 4.8 GHz Turbo Boost WiFi 6 & 2.5G LAN Connectivity 512GB NVMe SSD Storage GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe

**Brand:** gmktec
**Price:** 11292 kr
**Availability:** ✅ In Stock

## Summary

> 🚀 Power Meets Portability: The Mini PC That Means Business

## Quick Answers

- **What is this?** GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe by gmktec
- **How much does it cost?** 11292 kr with free shipping
- **Is it available?** Yes, in stock and ready to ship
- **Where can I buy it?** [www.desertcart.no](https://www.desertcart.no/products/706886749-gmktec-m2-pro-s-mini-pc-intel-core-i7-1185g7)

## Best For

- gmktec enthusiasts

## Why This Product

- Trusted gmktec brand quality
- Free international shipping included
- Worldwide delivery with tracking
- 15-day hassle-free returns

## Key Features

- • **Compact Powerhouse Design:** Sleek, space-saving mini PC that fits perfectly on any desk without compromising on performance—ideal for the modern professional on the go.
- • **Blazing Fast Intel Core i7:** Experience powerhouse performance with 4 cores, 8 threads, and turbo speeds up to 4.8 GHz—outpacing older i7 and i5 models effortlessly.
- • **Massive & Expandable Memory:** 16GB DDR4 RAM ready for expansion up to 64GB, paired with a lightning-fast 512GB NVMe SSD that can grow to 2TB—future-proof your productivity.
- • **Seamless Ultra-Fast Connectivity:** Stay connected with cutting-edge WiFi 6, Bluetooth 5.2, USB4.0, dual HDMI, DisplayPort, and ultra-reliable 2.5G Ethernet for all your peripherals and networks.
- • **Next-Level Graphics with Intel Iris Xe:** Unlock 5× better graphics performance for smooth multi-monitor setups, creative workflows, and casual gaming on 3 simultaneous 4K UHD displays.

## Overview

The GMKtec M2 Pro S Mini PC is a compact yet powerful desktop solution featuring an 11th Gen Intel Core i7-1185G7 processor with turbo speeds up to 4.8 GHz, Intel Iris Xe Graphics G7 for superior visuals, and 16GB DDR4 RAM paired with a 512GB NVMe SSD. It supports triple 4K UHD displays, offers extensive connectivity including WiFi 6, USB4.0, Bluetooth 5.2, and 2.5G LAN, all housed in a sleek mini form factor designed for professionals seeking high performance without the bulk.

## Description

desertcart.com: GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe | 16GB DDR4 512GB SSD, Desktop Mini Computers WiFi 6, USB4.0, BT 5.2, DP, HDMI, RJ45 2.5G LAN : Electronics

Review: GMKTec EVO-T1: A Mini-PC Worthy of Your Family’s AI-Learning Journey? - GMKTec EVO-T1: A Mini-PC Worthy of Your Family’s AI-Learning Journey? Is the GMKTec EVO-T1 an excellent choice for your school age children (grandchildren) to learn and build a solid foundation in AI tools while being capable of supporting more advanced AI development and experimentation as their interest and skills grow? As a Grandparent who attended High School during the early days of the development of Personal Computing, I know firsthand how valuable it can be to have easy access to technology tools to experience, learn and experiment with developing technologies. Having access to these tools can provide a lifelong knowledge base that could lead to meaningful opportunities. Developing a solid technology skill base today is even more important than when I was a student. AI technology development is progressing so much more rapidly than in the past that I fear that if my grandchildren do not get on the learning train early, they might find themselves left shut out of future opportunities and find that catching up to their peers is an impossible task. One of the most satisfying and impactful gifts I can give them is the tools and opportunity today to learn skills that they can call upon to succeed in the future. This was the basis for my purchase of the GMKtec EVO-T1. No doubt with its technology leading Intel Core Ultra 9 285H CPU and ARC 140T iGPU, it can easily handle any computing task that my family could ask it to do. The capability to upgrade the RAM from the included 64 MB to 128 MB and outfit it with up to three M2 NVME storage drives allows for future expansion. I was also impressed with the array of IO options available such as Audio ports front and back, dual 2.5 GB Lan ports and an Oculink port to support adding a separate GPU card to either support the needs of demanding game play or more demanding AI computation models and tools. This level of hardware should allow the GMKTec EVO-T1 to function in almost any other technology roll such as a Home Server, Router or NAS long after my Grandchildren have outgrown and moved past its role as an AI learning and development platform. The attractive and compact design ensures it fits easily into a home office or workspace and with its cooling capabilities it does not create a noisy environment that might distract or take away from an effective learning environment. I want to provide a capable technology device for my family to learn and develop AI skills beyond those provided by built in Internet connected LLM models offered to most computer user. I selected the GMKtec EVO-T1 believing it is up to this task and more. I want it to fill the gap between those that are highly advanced with AI development and require high end multi-GPU hardware in a dedicated AI Lab and what is currently available to novice AI users as part of most consumer computing hardware and software. At the same I wanted it to provide the added security and privacy of local AI usage thus removing the need to be tied to the public internet or to subscription fee models. Here is my assessment of how well the GMKtec EVO-T1 meets my needs and hopefully it will be of use in your purchasing decision. Most basic AI tasks start with using LLM’s through text-based prompts to have the AI models provide some answer to the prompt. To allow for easier access to these models several AI GUI wrapper applications are available. I tested the following AI GUI applications with several of the same prompts on the GMKtec EVO-T1 to ensure operations and determine if there were any issues. All these AI Wrappers perform their function and which one you choose as your daily driver will be an individual choice. I have included some brief notes beside each one based upon my impressions. AIPC This is the default application provided on the desktop. It has several advanced capabilities beyond simple prompt-based queries and provides them in a logical structure such as document analysis, translation, meeting minutes and image retrieval all accessed under the Skills menu. It also provides a LLM Model/App Store tab which allows access to eight popular LLM’s models locally along with the ability to also access many more paid Internet connected models and tools. You can use the AIPC application completely locally by simply clicking the “Offline Mode” selection on the screen following application launch. Or if you wish to utilize the Internet AI capabilities then on the launch screen you enter your email address and click on the “Send Code” button. Following receiving the code you enter it in the “Verification Code” field, check the User Agreement box and click “Login.” I found this application to be feature rich and convenient for most normal AI interactions along with providing several more advanced capabilities that might be of use. From my inquiries the GMKtec team authorizes and approves the addition of any LLM’s that are provided on the local selection to ensure security and useability. Given that this application is new it is still evolving, and documentation and screens are not yet polished for an English audience. Given the ease of use of the application for a wide audience I am sure any improvements will arrive in short order. LM Studio, JAN & AI Playground for Intel ARC All these GUI wrappers provide basic functionality and additional features that might be useful. I have listed these together because when tested they all fully utilized the GMKtec EVO_T1 Intel Arc 140T iGPU. One caveat is that many other tools natively support the Nvidia GPU. Therefore, they require some more advanced configurations to allow us to utilize the iGPU instead of only the CPU. While my testing shows the Core Ultra 9 285H CPU does a respectable job while executing AI LLM functions it does not perform this task as fast and as effectively as the Intel ARC 140T iGPU. If speed of execution is desired, then you would want to investigate advanced configurations by searching PyTorch and ipex.llm and learning how to configure those within the other AI GUI wrapper applications. LM Studio allows for almost any Open Source LLM model to be downloaded for local use and provides a well-integrated API back end as well as RAG integration. JAN provides one of the easiest GUI to navigate and use and also provides an API. While AI Playground for Intel ARC provides full and deep utilization of the Intel libraries and iGPU hardware. This allows for the use of CPU, NPU or iGPU selection while providing some preconfigured tools to accomplish image enhancement, text to image and text to video AI Generation within this GUI. A nice capability for the user. GPT4All, Ollama, OpenWebUI, Msty, Cherry Studio, Anything LLM I found that these tools utilize the Intel CPU and do not support the Intel ARC iGPU natively out of the box. My earlier comment that additional configurations work is needed to allow for iGPU use applies. I have confidence that some if not all these models will provide native use of the Intel iGPU in future releases and thus expand options for local model use. So, what might be expected for Tokens/second results for local models run on the GMKtec EVO-T1 and what are its real-world functional capabilities? To answer this question, I ran samples in each of the following Generative AI functional areas. AI LLM Chat, Text to Image, Text to Video and AI Agents. AI LLM Chat was tested with a variety of prompts including plain text, document analysis, and coding. In each case my results only represent the average Tokens/sec not the quality of the output. From this data a few conclusions on the performance of the GMKTec EVO-T1 can be made. Each model was tested with the CPU and the iGPU as the main AI computational device as shown in the results. Mistralv03:7b - CPU 9.95 T/s GPU 17.4 T/s MINICPM-V - CPU 5.9 T/s GPU 9.8 T/s QWQ:32b Q4 KM - CPU 2.7 T/s GPU 3.6 T/s LLAMA3.1 :8b - CPU 11.8 T/s GPU 13.6 T/s QWEN2.5:14b - CPU 6.2 T/s GPU 7.2 T/s QWEN2.5:7b - CPU 10.6 T/s GPU 14.3 T/s QWEN3-coder:30b - CPU 9.2 T/s GPU 19.1 T/s DEEPSEEK_R1 :32b - CPU 2.8 T/s GPU 3.5 T/s DEEPSEEK_R1 :14b - CPU 5.3 T/s GPU 7.9 DEEPSEEK_R1:8b - CPU 10.2 T/s GPU 15.6 T/s GPT-OSS:20b - CPU 11.8 T/s GPU 15.5 In evaluating these results, I personally use the benchmark of my reading speed ability. Meaning that if I am waiting for text to display while reading then performance seems slow, and this would not be an effective use of my time. This benchmark will vary by person, but I find for me anything around 4-6 T/s is a comfortable reading speed to ensure understanding. Hence some of the 32b models when utilizing the iGPU are close to meeting this benchmark and I would find them useful when being executed on the EVO-T1. For text to image and text to video several tools were used but primarily Comfy.UI. In all testing cases results with image generation finished in a reasonable time of less than a minute but with video generation this time expanded considerably depending upon settings. I find this functionality to be useable for learning and basic tasks on the EVO-T1. If video generation needs are higher for speed and resolution, then it is comforting to know that the EVO-T1 provides for this and other more demanding VRAM capabilities by including an Oculink port so that a separate and much more powerful GPU can be installed and utilized. Unfortunately, I do not have a more powerful GPU available, so this capability was not tested. To examine the GMKtec EVO-T1 performance with the execution of AI Agents I utilized n8n installed in a Docker Container on the Windows 11 operating system. Instructions are easily available to accomplish this and were easy to follow with the installation and operation going seamlessly. Several simple to complicated AI Agents were tested with workflows utilizing many node types calling both local and Internet LLM’s, Websites, API, and Data Bases. The GMKtec EVO-T1 with its powerful Core Ultra 9 285H CPU and 64 MB of RAM ensured that all steps and function worked quickly and flawlessly. Clearly this hardware with the selection of an appropriate high T/s local LLM makes the EVO-T1 a powerful AI Agent development and operational tool. Summary From my testing I can say with confidence that the EVO-T1 is well equipped and highly capable of providing the family with the tools to explore and learn AI tools today while easily scaling up for more demanding family members to expand their capabilities deeper into developing, learning and experimenting with the tools of AI.
Review: Powerful Home Workstation or Home Lab Server - Wow, the GMKtec Nucbox K10 is fast and powerful filling the role as an advanced Workstation or a Home Lab server running a Proxmox high availability cluster. In my testing with both cases, it performed impressively. If you have more advanced needs for your computer other than reading emails, checking social media and some internet surfing then you know how quickly the responsiveness of your computer can deteriorate when subjected to intensive memory/ CPU tasks. In my case I typically have half a dozen or more Windows virtual desktops open. In each desktop I will be simultaneously running application for 3D CAD design, multiple browsers, several videos for viewing and editing along with some equipment control GUI’s which heavily load down the CPU. Operating the GMKtec K10 with my normal daily workstation configuration and with a heavily loaded combination was snappy and it performed flawlessly. The K10 Bios was set to Performance mode, and I rarely heard the fan while it was located only two feet away. The normal working power consumption ran around 45 watts while less than 20 watts when idle. Every now and then when needed the power consumption would jump to the 90-watt range and I could hear the additional cooling kick in, but the noise was not obtrusive or distracting. I was impressed with the speed at which tasks were executed. Many which I normally must wait to wait a second or two to complete were done almost immediately. Rendering detailed 3D designs, Video edits and even loading web pages all were more responsive. Often while researching I can have a couple of dozen web pages open at a time and depending upon the browser being used this can have a visible impact on web page responsiveness. This was not an issue while using the K10. Next, I used the GMKtec K10 as my primary Proxmox server within a High Availability Cluster and it showed the same snappy response. It was clear that it was able to easily handle the dozen or more LXC/Docker Containers and Virtual Machines that I have distributed across two Proxmox Servers. As a test I moved all the containers and VM’s over to the K10 and then started them all and accessed three different operating systems within Virtual Machines from separate clients. It was nice to see that the K10 did not experience any lags or performance issues while using the clients simultaneously. On the hardware side of things, I tested the operation of all ports and found them to be up to specifications. The one standout was the long-range capabilities offered by the external antennas. I was able to connect and experience Wi-Fi 6 speeds with one of my attic access point located two floors away from the basement. I normally utilize wired connections for all devices, when possible, but it was impressive to know that a high-speed Wi-Fi connection could be achieve even if the access point is far away with the K10 should it be needed. My disk read/write testing showed that GMKtec had supplied an upper tier NVME drive in the K10 package. At this price point that was a nice bonus. Old school but I do maintain a remotely controlled Amateur Radio station in my house which has several control devices and interfaces to accomplish switching and antenna control. Some of these utilize RS 232 Com ports so I hooked those directly to the K10 RS232 port to confirm its operation and capability. No issues were noted, and the operation was as expected. Although I was impressed with how the GMKtec K10 will improve my daily experience while using either my Proxmox Server or Home Workstation it does have a few areas that might be important for other use cases. I am a casual gamer at best and with my limited testing the K10 performed up to a level of my ability. However, my son, who is more of a hard-core gamer, used the K10 and mentioned in general it was very capable but on some games the GPU capabilities were limiting the experience. On my personal list of skills to learn is to become familiar with the use of AI functionality to enhance daily tasks at home. I have not ventured very deeply into this area mainly because I wish to utilize local AI models and my computers to date have not been able to deliver an enjoyable experience with AI due to CPU and GPU constraints. To this end I briefly tested some local AI models on the K10. It was able to easily run the DeepSeek r1 8b model very well with snappy response. The K10 would also run the DeepSeek r1 70b model but it was rather slow with its responses. In summary if you’re not some who demands top tier gaming performance or the ability to utilize the largest AI models locally then you will find the GMKtec K10 to be up to almost every other task you can throw at it.

## Features

- 【Powerful Performance】GMKtec M2 Pro S mini computer is equipped with 11th generation Intel Core i7-1185G7 processor, main frequency up to 4.8 GHz, 4 cores, 8 threads, 12MB cache, running much faster than i7-10810U, i5-12450H and i5-8259U, Wins PC series The power is only 35W, supporting your daily work with less power consumption, without delaying daily tasks
- GMKtec M2 Pro S Mini PC with Intel Iris Xe Graphics G7 96EU GPU — Powered by Intel Iris Xe Graphics G7 with 96 Execution Units, delivering up to 5× higher graphics performance than entry-level integrated GPUs. Enjoy smoother multi-monitor output, faster media processing, and playable casual gaming. Designed for users who need real GPU performance for productivity, creative tasks, and immersive visuals — not just basic display output.
- 【Storage Capacity】16GB DDR4 and 512GB NVME SSD Desktop computer Comes with 16GB SODIMM, dual-channel DDR4 supports expansion up to 64GB. 512GB SSD M.2 2280 NVMe (PCIe3.0), supports expansion to 2TB, in addition, M.2 2242 SATA can be expanded to 2TB
- 【Wide Connectivity】The GMKtec M2 Pro S mini computer supports a range of connectivity options, including WiFi 6, USB4.0, BT 5.2, DP, HDMI, and RJ45 2.5G, allowing you to connect to multiple devices and peripherals from a single device.
- 【4K UHD & 3 Screens Support】Mini PC with Intel Iris Xe Graphics G7 96EU GPU delivers high-quality graphics for the most demanding applications, 2 x HDMI (4K @ 60Hz) and 1 x USB Type-C (4K @ 60Hz) output terminals, allowing you to independently display 4K screens on 3 displays at the same time
- 【Compact Design】The GMKtec M2 Pro S mini computer features a sleek and compact design that takes up minimal desk space, while providing maximum performance and functionality. Ideal for those who need a powerful computing solution in a small form factor.
- 【GMKtec Warranty 】GMKtec offers a 1-year limited warranty for each mini PC, starting from the date of the purchase. All defects due to design and workmanship are covered. With a professional after sales team always ready to attend to your needs, you can simply relax and enjoy your mini PC.

## Technical Specifications

| Specification | Value |
|---------------|-------|
| ASIN | B0D79439GH |
| Additional Features | Intel Core i7-1185G7, Intel Iris Xe Graphics G7 96EU GPU |
| Aspect Ratio | 16:9 |
| Best Sellers Rank | #3,255 in Computers & Accessories ( See Top 100 in Computers & Accessories ) #110 in Mini Computers |
| Brand | GMKtec |
| Built-In Media | 1x GMKtec Nucbox M2 Pro S Mini PC, 1× Screws, 1×Connection Cable, 1×HDMI Cable, 1×Power Adapter |
| CPU Model | Core i7 |
| CPU Model Number | Intel Core i7-1185G7 |
| CPU Model Speed Maximum | 4.8 GHz |
| CPU Speed | 5 GHz |
| Cache Memory Installed Size | 512 GB |
| Cache Size | 512 GB |
| Color | Black |
| Compatible Devices | Headphone, Keyboard, Mouse, Projector, Television |
| Connectivity Technology | HDMI, LAN, USB |
| Cooling Method | Air |
| Customer Reviews | 4.5 out of 5 stars 209 Reviews |
| Display Resolution Maximum | 4096x2160 pixels_per_inch |
| Display Type | LED, LCD, OLED |
| Graphics Card Description | Integrated |
| Graphics Card Interface | Integrated |
| Graphics Card Ram | 16 GB |
| Graphics Coprocessor | Intel Iris Xe Graphics G7 96EU |
| Graphics Description | Integrated |
| Graphics Ram Type | DDR4 SDRAM |
| Hard Disk Description | M.2 2280 PCIE 3.0/4.0 SSD DUAL Slots |
| Hard Disk Interface | PCIE x 16 |
| Hardware Interface | Bluetooth |
| Human-Interface Input | Mouse |
| Item Dimensions | 5.2 x 4.92 x 2.28 inches |
| Item Weight | 1.46 kg |
| Keyboard Layout | QWERTY |
| Manufacturer | GMKtec |
| Memory Clock Speed | 4800 MHz |
| Memory Slots Available | 2 |
| Memory Speed | 3200 mt_s |
| Memory Storage Capacity | 16 GB |
| Model Name | M2 Pro S |
| Model Number | MINI PC-Mxilie |
| Model Year | 2025 |
| Native Resolution | 4096x2160 |
| Number of Component Outputs | 1 |
| Operating System | OS Pro |
| Personal Computer Design Type | Mini PC |
| Power Consumption | 45 watts |
| Power Plug Type | Type C |
| Processor Brand | Intel |
| Processor Count | 8 |
| Processor Series | Core i7 |
| Processor Socket | FCBGA1449 |
| Processor Speed | 5 GHz |
| RAM Memory Installed | 16 GB |
| RAM Memory Technology | DDR4 |
| RAM Type | DDR4 SDRAM |
| Ram Memory Maximum Size | 64 GB |
| Resolution | 4096x2160 |
| Security Features | Basic security features |
| Specific Uses For Product | Business, Gaming |
| Specification Met | CE |
| Style Name | i7-1185G7 |
| Total Number of HDMI Ports | 2 |
| Total Usb Ports | 6 |
| Video Output | HDMI, Type-C |
| Video Output Interface | DisplayPort, HDMI |
| Video Processor | Intel |
| Warranty Description | 1 Year |
| Wireless Compability | 2.4 GHz Radio Frequency, 5 GHz Radio Frequency, 802.11ax, Bluetooth |
| Wireless Network Technology | Wi-Fi |
| Wireless Technology | Bluetooth, Wi-Fi |

## Product Details

- **Brand:** GMKtec
- **CPU Model:** Core i7
- **CPU Speed:** 5 GHz
- **Cache Size:** 512 GB
- **Graphics Card Description:** Integrated
- **Graphics Coprocessor:** Intel Iris Xe Graphics G7 96EU
- **Memory Storage Capacity:** 16 GB
- **Operating System:** OS Pro
- **Personal computer design type:** Mini PC
- **Specific Uses For Product:** Business, Gaming

## Images

![GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe - Image 1](https://m.media-amazon.com/images/I/61F6FlnsH8L.jpg)
![GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe - Image 2](https://m.media-amazon.com/images/I/712+rhZw9vL.jpg)
![GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe - Image 3](https://m.media-amazon.com/images/I/51h61xpejWL.jpg)
![GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe - Image 4](https://m.media-amazon.com/images/I/816jvfYrr9L.jpg)
![GMKtec M2 Pro S Mini PC Intel Core i7-1185G7 (Turbo 4.8 GHz) Intel Iris Xe - Image 5](https://m.media-amazon.com/images/I/61TzFXEDV8L.jpg)

## Available Options

This product comes in different **Size** options.

## Customer Reviews

### ⭐⭐⭐⭐⭐ GMKTec EVO-T1: A Mini-PC Worthy of Your Family’s AI-Learning Journey?
*by A***R on September 7, 2025*

GMKTec EVO-T1: A Mini-PC Worthy of Your Family’s AI-Learning Journey? Is the GMKTec EVO-T1 an excellent choice for your school age children (grandchildren) to learn and build a solid foundation in AI tools while being capable of supporting more advanced AI development and experimentation as their interest and skills grow? As a Grandparent who attended High School during the early days of the development of Personal Computing, I know firsthand how valuable it can be to have easy access to technology tools to experience, learn and experiment with developing technologies. Having access to these tools can provide a lifelong knowledge base that could lead to meaningful opportunities. Developing a solid technology skill base today is even more important than when I was a student. AI technology development is progressing so much more rapidly than in the past that I fear that if my grandchildren do not get on the learning train early, they might find themselves left shut out of future opportunities and find that catching up to their peers is an impossible task. One of the most satisfying and impactful gifts I can give them is the tools and opportunity today to learn skills that they can call upon to succeed in the future. This was the basis for my purchase of the GMKtec EVO-T1. No doubt with its technology leading Intel Core Ultra 9 285H CPU and ARC 140T iGPU, it can easily handle any computing task that my family could ask it to do. The capability to upgrade the RAM from the included 64 MB to 128 MB and outfit it with up to three M2 NVME storage drives allows for future expansion. I was also impressed with the array of IO options available such as Audio ports front and back, dual 2.5 GB Lan ports and an Oculink port to support adding a separate GPU card to either support the needs of demanding game play or more demanding AI computation models and tools. This level of hardware should allow the GMKTec EVO-T1 to function in almost any other technology roll such as a Home Server, Router or NAS long after my Grandchildren have outgrown and moved past its role as an AI learning and development platform. The attractive and compact design ensures it fits easily into a home office or workspace and with its cooling capabilities it does not create a noisy environment that might distract or take away from an effective learning environment. I want to provide a capable technology device for my family to learn and develop AI skills beyond those provided by built in Internet connected LLM models offered to most computer user. I selected the GMKtec EVO-T1 believing it is up to this task and more. I want it to fill the gap between those that are highly advanced with AI development and require high end multi-GPU hardware in a dedicated AI Lab and what is currently available to novice AI users as part of most consumer computing hardware and software. At the same I wanted it to provide the added security and privacy of local AI usage thus removing the need to be tied to the public internet or to subscription fee models. Here is my assessment of how well the GMKtec EVO-T1 meets my needs and hopefully it will be of use in your purchasing decision. Most basic AI tasks start with using LLM’s through text-based prompts to have the AI models provide some answer to the prompt. To allow for easier access to these models several AI GUI wrapper applications are available. I tested the following AI GUI applications with several of the same prompts on the GMKtec EVO-T1 to ensure operations and determine if there were any issues. All these AI Wrappers perform their function and which one you choose as your daily driver will be an individual choice. I have included some brief notes beside each one based upon my impressions. AIPC This is the default application provided on the desktop. It has several advanced capabilities beyond simple prompt-based queries and provides them in a logical structure such as document analysis, translation, meeting minutes and image retrieval all accessed under the Skills menu. It also provides a LLM Model/App Store tab which allows access to eight popular LLM’s models locally along with the ability to also access many more paid Internet connected models and tools. You can use the AIPC application completely locally by simply clicking the “Offline Mode” selection on the screen following application launch. Or if you wish to utilize the Internet AI capabilities then on the launch screen you enter your email address and click on the “Send Code” button. Following receiving the code you enter it in the “Verification Code” field, check the User Agreement box and click “Login.” I found this application to be feature rich and convenient for most normal AI interactions along with providing several more advanced capabilities that might be of use. From my inquiries the GMKtec team authorizes and approves the addition of any LLM’s that are provided on the local selection to ensure security and useability. Given that this application is new it is still evolving, and documentation and screens are not yet polished for an English audience. Given the ease of use of the application for a wide audience I am sure any improvements will arrive in short order. LM Studio, JAN & AI Playground for Intel ARC All these GUI wrappers provide basic functionality and additional features that might be useful. I have listed these together because when tested they all fully utilized the GMKtec EVO_T1 Intel Arc 140T iGPU. One caveat is that many other tools natively support the Nvidia GPU. Therefore, they require some more advanced configurations to allow us to utilize the iGPU instead of only the CPU. While my testing shows the Core Ultra 9 285H CPU does a respectable job while executing AI LLM functions it does not perform this task as fast and as effectively as the Intel ARC 140T iGPU. If speed of execution is desired, then you would want to investigate advanced configurations by searching PyTorch and ipex.llm and learning how to configure those within the other AI GUI wrapper applications. LM Studio allows for almost any Open Source LLM model to be downloaded for local use and provides a well-integrated API back end as well as RAG integration. JAN provides one of the easiest GUI to navigate and use and also provides an API. While AI Playground for Intel ARC provides full and deep utilization of the Intel libraries and iGPU hardware. This allows for the use of CPU, NPU or iGPU selection while providing some preconfigured tools to accomplish image enhancement, text to image and text to video AI Generation within this GUI. A nice capability for the user. GPT4All, Ollama, OpenWebUI, Msty, Cherry Studio, Anything LLM I found that these tools utilize the Intel CPU and do not support the Intel ARC iGPU natively out of the box. My earlier comment that additional configurations work is needed to allow for iGPU use applies. I have confidence that some if not all these models will provide native use of the Intel iGPU in future releases and thus expand options for local model use. So, what might be expected for Tokens/second results for local models run on the GMKtec EVO-T1 and what are its real-world functional capabilities? To answer this question, I ran samples in each of the following Generative AI functional areas. AI LLM Chat, Text to Image, Text to Video and AI Agents. AI LLM Chat was tested with a variety of prompts including plain text, document analysis, and coding. In each case my results only represent the average Tokens/sec not the quality of the output. From this data a few conclusions on the performance of the GMKTec EVO-T1 can be made. Each model was tested with the CPU and the iGPU as the main AI computational device as shown in the results. Mistralv03:7b - CPU 9.95 T/s GPU 17.4 T/s MINICPM-V - CPU 5.9 T/s GPU 9.8 T/s QWQ:32b Q4 KM - CPU 2.7 T/s GPU 3.6 T/s LLAMA3.1 :8b - CPU 11.8 T/s GPU 13.6 T/s QWEN2.5:14b - CPU 6.2 T/s GPU 7.2 T/s QWEN2.5:7b - CPU 10.6 T/s GPU 14.3 T/s QWEN3-coder:30b - CPU 9.2 T/s GPU 19.1 T/s DEEPSEEK_R1 :32b - CPU 2.8 T/s GPU 3.5 T/s DEEPSEEK_R1 :14b - CPU 5.3 T/s GPU 7.9 DEEPSEEK_R1:8b - CPU 10.2 T/s GPU 15.6 T/s GPT-OSS:20b - CPU 11.8 T/s GPU 15.5 In evaluating these results, I personally use the benchmark of my reading speed ability. Meaning that if I am waiting for text to display while reading then performance seems slow, and this would not be an effective use of my time. This benchmark will vary by person, but I find for me anything around 4-6 T/s is a comfortable reading speed to ensure understanding. Hence some of the 32b models when utilizing the iGPU are close to meeting this benchmark and I would find them useful when being executed on the EVO-T1. For text to image and text to video several tools were used but primarily Comfy.UI. In all testing cases results with image generation finished in a reasonable time of less than a minute but with video generation this time expanded considerably depending upon settings. I find this functionality to be useable for learning and basic tasks on the EVO-T1. If video generation needs are higher for speed and resolution, then it is comforting to know that the EVO-T1 provides for this and other more demanding VRAM capabilities by including an Oculink port so that a separate and much more powerful GPU can be installed and utilized. Unfortunately, I do not have a more powerful GPU available, so this capability was not tested. To examine the GMKtec EVO-T1 performance with the execution of AI Agents I utilized n8n installed in a Docker Container on the Windows 11 operating system. Instructions are easily available to accomplish this and were easy to follow with the installation and operation going seamlessly. Several simple to complicated AI Agents were tested with workflows utilizing many node types calling both local and Internet LLM’s, Websites, API, and Data Bases. The GMKtec EVO-T1 with its powerful Core Ultra 9 285H CPU and 64 MB of RAM ensured that all steps and function worked quickly and flawlessly. Clearly this hardware with the selection of an appropriate high T/s local LLM makes the EVO-T1 a powerful AI Agent development and operational tool. Summary From my testing I can say with confidence that the EVO-T1 is well equipped and highly capable of providing the family with the tools to explore and learn AI tools today while easily scaling up for more demanding family members to expand their capabilities deeper into developing, learning and experimenting with the tools of AI.

### ⭐⭐⭐⭐⭐ Powerful Home Workstation or Home Lab Server
*by J***K on May 20, 2025*

Wow, the GMKtec Nucbox K10 is fast and powerful filling the role as an advanced Workstation or a Home Lab server running a Proxmox high availability cluster. In my testing with both cases, it performed impressively. If you have more advanced needs for your computer other than reading emails, checking social media and some internet surfing then you know how quickly the responsiveness of your computer can deteriorate when subjected to intensive memory/ CPU tasks. In my case I typically have half a dozen or more Windows virtual desktops open. In each desktop I will be simultaneously running application for 3D CAD design, multiple browsers, several videos for viewing and editing along with some equipment control GUI’s which heavily load down the CPU. Operating the GMKtec K10 with my normal daily workstation configuration and with a heavily loaded combination was snappy and it performed flawlessly. The K10 Bios was set to Performance mode, and I rarely heard the fan while it was located only two feet away. The normal working power consumption ran around 45 watts while less than 20 watts when idle. Every now and then when needed the power consumption would jump to the 90-watt range and I could hear the additional cooling kick in, but the noise was not obtrusive or distracting. I was impressed with the speed at which tasks were executed. Many which I normally must wait to wait a second or two to complete were done almost immediately. Rendering detailed 3D designs, Video edits and even loading web pages all were more responsive. Often while researching I can have a couple of dozen web pages open at a time and depending upon the browser being used this can have a visible impact on web page responsiveness. This was not an issue while using the K10. Next, I used the GMKtec K10 as my primary Proxmox server within a High Availability Cluster and it showed the same snappy response. It was clear that it was able to easily handle the dozen or more LXC/Docker Containers and Virtual Machines that I have distributed across two Proxmox Servers. As a test I moved all the containers and VM’s over to the K10 and then started them all and accessed three different operating systems within Virtual Machines from separate clients. It was nice to see that the K10 did not experience any lags or performance issues while using the clients simultaneously. On the hardware side of things, I tested the operation of all ports and found them to be up to specifications. The one standout was the long-range capabilities offered by the external antennas. I was able to connect and experience Wi-Fi 6 speeds with one of my attic access point located two floors away from the basement. I normally utilize wired connections for all devices, when possible, but it was impressive to know that a high-speed Wi-Fi connection could be achieve even if the access point is far away with the K10 should it be needed. My disk read/write testing showed that GMKtec had supplied an upper tier NVME drive in the K10 package. At this price point that was a nice bonus. Old school but I do maintain a remotely controlled Amateur Radio station in my house which has several control devices and interfaces to accomplish switching and antenna control. Some of these utilize RS 232 Com ports so I hooked those directly to the K10 RS232 port to confirm its operation and capability. No issues were noted, and the operation was as expected. Although I was impressed with how the GMKtec K10 will improve my daily experience while using either my Proxmox Server or Home Workstation it does have a few areas that might be important for other use cases. I am a casual gamer at best and with my limited testing the K10 performed up to a level of my ability. However, my son, who is more of a hard-core gamer, used the K10 and mentioned in general it was very capable but on some games the GPU capabilities were limiting the experience. On my personal list of skills to learn is to become familiar with the use of AI functionality to enhance daily tasks at home. I have not ventured very deeply into this area mainly because I wish to utilize local AI models and my computers to date have not been able to deliver an enjoyable experience with AI due to CPU and GPU constraints. To this end I briefly tested some local AI models on the K10. It was able to easily run the DeepSeek r1 8b model very well with snappy response. The K10 would also run the DeepSeek r1 70b model but it was rather slow with its responses. In summary if you’re not some who demands top tier gaming performance or the ability to utilize the largest AI models locally then you will find the GMKtec K10 to be up to almost every other task you can throw at it.

### ⭐⭐⭐⭐⭐ A GREAT COMPUTER, THE BEST BANG FOR THE BUCK!
*by H***R on June 12, 2025*

I dare you to find a better bargain. These are the specs (much of it not shown on their page): Windows 11 pro (without bloatware), 1TB of SSD memory, 13th gen i9 Intel processor with 14 cores at 20 threads [specifically it is divided (A-Core: 6x Raptor Cove standard operating at 2.60 GHz, up to 5.40 GHz) & (B-Core: 8x Gracemont 1.90 GHz, up to 4.10 GHz)], 64 GB of DDR5, graphics card is an Intel Iris Xe (only 128mb however, it does draw from the RAM as well, so it has a capacity of up to 32 GB, and with so much RAM on this rig it's a good compromise), four regular 2.0 usb, AND four 3.2 gen2 usb (10 GB each), 2 hdmi and 1 DP (on their page it states 60 Hz each however, it does modify, I have the monitor set for 165 Hz and the computer card did automatically set for 165Hz), Wi-Fi 6e which is blazing fast (this is usually the one thing most economical brands tend to skip on and will give you the standard Wi-Fi 6). I don't believe you could find this configuration in any other rig WITHOUT GOING WELL INTO THE 4 DIGITS (even if you factor in the cost of speakers, monitor, mouse and keyboard when comparing to laptops, which I bought all on Amazon for an additional $300, still under 4 digits). I hooked this thing up to a Sceptre 34-inch screen (3440 X 1440), and it's a beautiful display. Got some standard Creative speakers and the sound is still amazing. And a Logitech wireless mouse and keyboard. I live in the Arizona desert. I like windows open as much as possible; it's not uncommon for me to let the inside temps run to nearly 100 degrees before I wimp out and turn the AC on. I mention this only because this computer has been operating at those temps and doing so smoothly and seamlessly without any additional cooling measures (haven't found a laptop capable of that). It's a fast little beast, and it's still as quiet as can be. Yes, there is a minor hum, but it's about the same as a fan on any standard large computer. The only difference being that, since it is so small, it will inevitably lay on the desktop, so yeah, you will notice the sound more; however, it's really not a factor. To me, the major drawback is the power supply. It's an unexpectedly heavy-duty cord with a box about a 1/4 the size of the actual computer, lol. Since I did put it on the desktop, I had to be a little creative to not make it so encumbering; in my opinion, they could probably improve on the size. But equally so, it doesn't even heat up like you would see many laptop power supplies do; in the nearly 100 degree environment, it's hardly noticeably warm to the touch (my power supply to the monitor is much hotter). This purchase was the culmination of many long hours of research, which originally started with me replacing my laptop that died. I don't really need a laptop, so I started thinking outside the box and comparing possibilities from Best Buy, Walmart, and Amazon (MANY LONG HOURS!). The price on this was at my limit. It was loaded with everything I wanted (I expected to make compromises for this price point, happy to say I didn't have to). GMKtec's Amazon reviews are great on all the other models they offer; however, this one model sits on its own with few reviews. I felt it important to help spread the word here. All of this simply to say one thing: if you're on the fence, just stop already—you've hit the jackpot. BUY IT!

## Frequently Bought Together

- GMKtec Mini PC Workstation, Intel Core i9 13900HK(14C/20T) up to 5.4GHz, Mini Computer 64GB DDR5 RAM 1TB SSD with 8X USB Ports/COM/HDMI/DP for Office Business
- Logitech MK270 Wireless Keyboard and Mouse Combo for Windows, 2.4 GHz Wireless, Compact Mouse, 8 Multimedia and Shortcut Keys, 2-Year Battery Life, for PC, Laptop, QWERTY UK English Layout - Black
- Logitech TS-270004 MK270 Wireless Combo Keyboard and Mouse

---

## Why Shop on Desertcart?

- 🛒 **Trusted by 1.3+ Million Shoppers** — Serving international shoppers since 2016
- 🌍 **Shop Globally** — Access 737+ million products across 21 categories
- 💰 **No Hidden Fees** — All customs, duties, and taxes included in the price
- 🔄 **15-Day Free Returns** — Hassle-free returns (30 days for PRO members)
- 🔒 **Secure Payments** — Trusted payment options with buyer protection
- ⭐ **TrustPilot Rated 4.5/5** — Based on 8,000+ happy customer reviews

**Shop now:** [https://www.desertcart.no/products/706886749-gmktec-m2-pro-s-mini-pc-intel-core-i7-1185g7](https://www.desertcart.no/products/706886749-gmktec-m2-pro-s-mini-pc-intel-core-i7-1185g7)

---

*Product available on Desertcart Norway*
*Store origin: NO*
*Last updated: 2026-10-02*