Intermediate 13 minMini-PC

GMKtec EVO-X2: review for local AI, 64 or 128 GB

An open laptop casts green light across a dark desk.
Direct response

The GMKtec EVO-X2 is a Ryzen AI Max+ 395 mini PC whose soldered LPDDR5X memory (64 or 128 GB) is also used by the Radeon 8060S GPU. For local AI, the 128 GB version is the right choice: up to 96 GB for the GPU, enough to load gpt-oss 120B or Llama 4 Scout. On November 18, 2026, gmktec.fr lists it at €3,499.99 (128 GB + 2 TB) versus €2,029.99 for the 64 GB version.

The GMKtec EVO-X2 is one of the most frequently mentioned mini PCs for running large language models at home. This guide brings together the official spec sheet, public prices as of November 18, 2026, reviews from ServeTheHome and Tom's Hardware, and the settings documented by AMD. You'll find out whether it fits your use case, which memory configuration to choose, and how to set it up on Windows or Linux.

Choosing a machine? Our picks by budget → · Our spec sheet Ryzen AI Max mini-PC with 128 GB →

By Mohamed Meguedmi·Update 2026-11-18·Tested on Windows, macOS, and Linux
Recommended hardware

Good value for local AI: a GMKtec EVO-X2 — Amazon may show another configuration; check before buying.

A mini PC is a complete machine: check the available memory and engine compatibility. It does not replace macOS/MLX or CUDA.

Why this choice? Our complete guide on GMKtec EVO-X2 — Amazon may show another configuration; check before buying →

Compare all options by budget, from €800 to €3,500 →

Small budget: RTX 5060 · Large models: RTX 5090 · Mac Studio.

On the go: which laptop for local AI →

Affiliate links — commission possible at no extra cost to you. As an Amazon Associate, BestLLMfor earns from qualifying purchases.

Amazon may redirect you to a local store or show another configuration. Check the listing before buying; this link does not guarantee the destination or configuration.

#GMKtec EVO-X2: is it good for local AI?

The GMKtec EVO-X2 is a good choice for local AI if you want to load models with 60 to 90 GB of weights in a compact case, on Windows or Linux, and moderate speed is enough for you. It isn't a fast machine: it's a machine that offers a lot of graphics memory in a small case.

Unified memory is a single pool of memory shared by the CPU and the integrated GPU: with no separate VRAM, a 70 GB model fits in graphics memory, whereas a consumer graphics card tops out at 16 or 32 GB. According to AMD, up to 96 GB of the Ryzen AI Max+ 395's 128 GB can be allocated as VRAM on Windows.

The trade-off is bandwidth: AMD specifies 256 GB/s, far less than a high-end graphics card. A large dense model therefore runs slowly on the EVO-X2, while a mixture-of-experts (MoE) model, which activates only part of its weights for each token, remains comfortable to use.

Who it's for
Developers, freelancers, and small businesses that want a large local model (gpt-oss 120B, Llama 4 Scout) without a discrete graphics card.
Who it's not for
Anyone who wants maximum speed on small models, depends on CUDA, or worries about fan noise.

#What's inside the GMKtec EVO-X2? The specs that matter for AI

The GMKtec EVO-X2 combines a 16-core, 32-thread AMD Ryzen AI Max+ 395 processor, a Radeon 8060S integrated GPU with 40 RDNA 3.5 compute units, and 64 or 128 GB of soldered LPDDR5X. The gmktec.fr product page, accessed November 18, 2026, lists stable operation at 120 W, with peaks of 140 W.

GMKtec EVO-X2 specs relevant to local AI (gmktec.fr product page, November 18, 2026)
ItemPublished valueWhat this means for an LLM
ProcesseurRyzen AI Max+ 395, 16 cores / 32 threadsSufficient for data preparation and CPU computation
Integrated GPURadeon 8060S, 40 RDNA 3.5 coresRuns inference via ROCm or Vulkan
Memory64 or 128 GB LPDDR5X 8000 MHz, solderedSets the maximum model size, with no upgrade path
Memory bus256-bit (eight 32-bit controllers, according to GMKtec)256 GB/s bandwidth according to AMD: limits speed
Graphics memoryUp to 96 GB on the 128 GB version (AMD, GMKtec)Lets you load a 70 to 90 GB model
Power120 W sustained, peaks of 140 W; external power brick of about 230 WModest power draw for this capacity
Format193 x 185.8 x 77 mm; two M.2 slots, up to 16 TBFits on a desk, stores several large models

#How much does the GMKtec EVO-X2 cost in November 2026?

As of November 18, 2026, the official gmktec.fr store lists the GMKtec EVO-X2 at €2,029.99 for 64 GB + 1 TB and €3,499.99 for 128 GB + 2 TB. The struck-through prices are €2,299.99 and €3,599.99, respectively. The gap between the two versions is therefore €1,470.

Official retail prices of the GMKtec EVO-X2 and its siblings (GMKtec stores, November 18, 2026)
Model and configurationDisplayed priceCrossed-out price
EVO-X2, 64 GB + 1 TB2 029,99 €2 299,99 €
EVO-X2, 128 GB + 2 TB3 499,99 €3 599,99 €
EVO-X3, 128 GB + 2 TB (same processor, OCuLink port)3 599,99 €not listed
EVO-X5 Pro, 192 GB + 2 TB (Ryzen AI Max+ PRO 495)6 599,00 €not listed

GMKtec states on the same page that its prices are expected to rise in 2027 due to component costs, and offers a price guarantee until December 31, 2026. These prices change often during year-end promotions: check them on the official product page on the day you buy.

!
Returns: read the terms before you order
The gmktec.fr product page states that for a return of a non-defective product, including a change of mind, a 15% repackaging and restocking fee is deducted from the refund. On a €3,499.99 configuration, that comes to about €525. The stated warranty is 2 years.

#GMKtec EVO-X2 64 GB or 128 GB: which version should you choose?

For local AI, choose the 128 GB version of the GMKtec EVO-X2, unless you're only targeting models under 30 GB. The memory is soldered and GMKtec states it isn't upgradable: the choice you make at purchase is final, and what sets the EVO-X2 apart from a regular PC is precisely its large capacity.

GMKtec itself states the difference: DeepSeek-R1 32B for the 64 GB version, and DeepSeek-R1 70B and Llama 4 109B for the 128 GB version. On Linux, AMD's ROCm documentation states that the memory limit shared with the GPU defaults to about 50% of total memory, or about 32 GB on the 64 GB version until you raise it.

Which model to load for each EVO-X2 version (Q4 sizes, weights only, BestLLMfor catalog)
ModelWeights in Q4EVO-X2 64 GBEVO-X2 128 GB
gpt-oss 20B13 GBYesYes
Gemma 4 31B18 GBYesYes
Qwen 3.6 35B-A3B (MoE)21 GBYesYes
Qwen3-Coder-Next 80B-A3B (MoE)48 GBBorderline, short context (estimate)Yes
Llama 4 Scout 109B (MoE)65 GBNoYes
gpt-oss 120B (MoE)70 GBNoYes
Mistral Small 4 119B (MoE)72 GBNoYes, moderate context
GLM 5.3 Flash 320B-A18B (MoE)186 GBNoNo

The 64 GB column is based on an estimate: after reserving 12 to 16 GB for the system and applications, about 48 GB remain for the model and its context. But the context comes on top of the weights, and a long document can take several more gigabytes.

#How fast do LLMs run on the GMKtec EVO-X2?

For the GMKtec EVO-X2, GMKtec claims 13.83 to 57.15 tokens per second for MoE models, while ServeTheHome measured under 4 tokens per second for a dense 70-billion-parameter model. The available figures come from the manufacturer, AMD, and ServeTheHome; none were measured for this guide.

Published generation speeds for the EVO-X2 and the Ryzen AI Max+ 395 (status of each figure indicated)
ModelThroughputSource and status
gpt-oss 20B57.15 tokens/sAnnounced by GMKtec, 128 GB version
Qwen3 30B55.02 tokens/sAnnounced by GMKtec, 128 GB version
gpt-oss 120B19.25 tokens/sAnnounced by GMKtec, 128 GB version
Llama 4 Scout 109B Q4_K_M13.83 tokens/sClaimed by GMKtec; AMD claims up to 15 tokens/s
DeepSeek-R1 32B (dense)9.26 tokens/sAnnounced by GMKtec, 128 GB version
Llama 3.3 70B Q6_K (dense), fully on GPU3.7 to 3.8 tokens/sMeasured by ServeTheHome, review published July 11, 2025

The theoretical generation ceiling is roughly the bandwidth divided by the size of the weights read for each token. For a dense 70B model in Q4, about 40 GB, the estimate comes to 256 ÷ 40 ≈ 6.4 tokens per second at best. In Q6_K, this model takes up more than 50 GB according to ServeTheHome: the estimated ceiling drops to around 5 tokens per second, and the measured 3.7 to 3.8 stays below that.

With an MoE model, only the active experts are read for each token, which explains the 19.25 tokens per second reported for gpt-oss 120B despite 70 GB of weights. On the EVO-X2, favor gpt-oss 120B, Qwen 3.6 35B-A3B, or Qwen3-Coder-Next over a dense 70B model.

i
"2.2 times a RTX 4090": a figure that needs context
The GMKtec product page claims in LM Studio AI performance 2.2 times higher than a NVIDIA RTX 4090, without specifying the model or settings. A gap that large is only plausible for a model that exceeds the 24 GB of memory on the RTX 4090 and spills over into system memory. For a model that fits in 24 GB, don't rely on this figure: compare independent measurements.

#How do you configure the GMKtec EVO-X2 for local AI on Windows or Linux?

The GMKtec EVO-X2 ships with Windows 11 Pro, and GMKtec states it is compatible with Linux and Ubuntu. On Windows, increase the graphics memory in the AMD driver; on Linux, install a recent kernel and raise the limit on memory shared with the GPU.

#On Windows: Variable Graphics Memory and LM Studio

  1. 01
    Update the AMD driver
    Install the latest version of AMD Software: Adrenalin Edition. On July 29, 2025, AMD announced that the Adrenalin 25.8.1 driver lets you load models with up to 128 billion parameters in llama.cpp Vulkan on Windows.
  2. 02
    Increase graphics memory
    In AMD Software: Adrenalin Edition, open the Performance tab, then Tuning, and set Variable Graphics Memory, up to 96 GB on the 128 GB version. Restart if the software prompts you to.
  3. 03
    Configure LM Studio
    In LM Studio, check manual parameter selection and set GPU Offload to the maximum, as recommended by AMD, which also advises Q4_K_M quantization for everyday use.
  4. 04
    Verify that the GPU is working
    During generation, open Task Manager and go to the Performance tab: GPU memory should hold the model and the GPU should be active. If only the CPU is working, the model isn't loaded on the GPU.

For Ollama, the official documentation lists the Ryzen AI Max+ 395 among the chips supported by ROCm v7 on Linux, but not in its ROCm list for Windows, which is limited to Radeon RX 7000 and Radeon PRO. On the EVO-X2 under Windows, Ollama therefore relies on its Vulkan engine, which the same documentation says is enabled by default and already included with most Windows drivers.

#On Linux: recent kernel and shared memory limit

AMD's ROCm documentation requires Linux kernel 6.18.4 or later for Ryzen AI Max, or on Ubuntu 24.04 the HWE kernel 6.17.0-19.19~24.04.2 or later. AMD recommends keeping a small VRAM reservation in the BIOS, such as 0.5 GB, and instead raising the shared memory limit with the amd-ttm tool.

Linux (Ubuntu): raise the memory shared with the GPU, per AMD's ROCm documentation
sudo apt install pipx
pipx ensurepath
pipx install amd-debug-tools
amd-ttm
amd-ttm --set 100

Running amd-ttm on its own shows the current limit; amd-ttm --set 100 sets it to 100 GB after a reboot, and amd-ttm --clear restores the defaults. On the 64 GB version, choose a much lower value to leave memory for the system.

#What are the limitations of the GMKtec EVO-X2?

The GMKtec EVO-X2's main limitations are memory bandwidth, noise under load, non-upgradable memory, and the lack of CUDA, according to the official product page and reviews from ServeTheHome and Tom's Hardware.

Noise and power consumption
ServeTheHome measured 8 to 14 W and 37 to 38 dBA at idle, then 147 to 160 W and 41 to 43 dBA during Llama 3.3 70B Q6_K inference.
Finition
In its February 4, 2026 review, Tom's Hardware noted a cheap-looking case, an external power brick, a hard-to-access interior, and an audible fan.
No CUDA
The GPU is a Radeon: tools that require CUDA don't work; llama.cpp, LM Studio and Ollama run through ROCm or Vulkan.

Privacy depends on the software, not the machine: LM Studio, llama.cpp, and Ollama run the model locally. The AIPC app preinstalled by GMKtec was not examined for this guide; for sensitive data, use software you install and control yourself.

#GMKtec EVO-X2, EVO-X3, or EVO-X5 Pro: Buy Now or Wait?

Buy the GMKtec EVO-X2 128 GB now if your models fit in 96 GB and you want a local assistant today. Choose something else if you're targeting models larger than 96 GB, need CUDA, or want to connect an external graphics card.

Which mini PC to choose for your needs (GMKtec list prices as of November 18, 2026)
Your needsOptionWhy
MoE models up to 70 GB, tight budgetEVO-X2 128 GB + 2 TB, €3,499.99Up to 96 GB for the GPU, €100 less than the EVO-X3
Same needs, with an external GPU laterEVO-X3 128 GB + 2 TB, €3,599.99Same Ryzen AI Max+ 395, OCuLink PCIe Gen4 x4 port for an external GPU
Models larger than 96 GBEVO-X5 Pro 192 GB + 2 TB, €6,599.00Ryzen AI Max+ PRO 495 and 192 GB, at nearly double the price
Tools that require CUDANVIDIA machine (DGX Spark or GeForce card)The Radeon 8060S doesn't run CUDA
Models under 30 GB, speed above allPC with a 24 to 32 GB graphics cardDedicated graphics memory, faster for models that fit in it
→
What to check before you order
Add up the Q4 sizes of the models you'll use plus a few gigabytes for context. Above roughly 48 GB (estimate), the 64 GB version is ruled out; above 96 GB, the Windows limit, the EVO-X2 is ruled out too, except on Linux, where AMD shows a 100 GB setting on a 128 GB machine.
Frequently asked questions
Can the GMKtec EVO-X2 run a 70B model?+
Yes, the 128 GB version of the GMKtec EVO-X2 can load a dense 70-billion-parameter model, but slowly: ServeTheHome measured 3.7 to 3.8 tokens per second with Llama 3.3 70B in Q6_K, running entirely on the GPU. The 64 GB version isn't among the configurations GMKtec lists for DeepSeek-R1 70B.
Can you add memory to the GMKtec EVO-X2 later?+
No. GMKtec's official spec sheet describes soldered, non-upgradable LPDDR5X memory in 64 or 128 GB. Only storage can be expanded: the EVO-X2 has two M.2 2280 slots, for an advertised total of up to 16 TB. So you choose your memory once and for all when you buy.
Is the GMKtec EVO-X2 a good choice for coding with a local model?+
Yes, as long as you choose an MoE model. On the 128 GB GMKtec EVO-X2, Qwen3-Coder-Next 80B-A3B (48 GB in Q4) or gpt-oss 120B (70 GB) fit in graphics memory. A dense 70B coding model would be too slow for autocomplete, with an estimated ceiling of around 6 tokens per second.
Is the GMKtec EVO-X2 noisy?+
Moderately. ServeTheHome measured 37 to 38 dBA at idle and 41 to 43 dBA during Llama 3.3 70B inference, in a studio with a 34 dBA noise floor. Tom's Hardware lists fan noise among the EVO-X2's drawbacks. Performance modes let you reduce it at the cost of speed.
Should you choose a NVIDIA DGX Spark over the GMKtec EVO-X2?+
NVIDIA's DGX Spark comes with 64 or 128 GB of unified memory and 273 GB/s of bandwidth according to NVIDIA, versus 256 GB/s for the GMKtec EVO-X2 according to AMD. The DGX Spark is built on a Blackwell GPU, CUDA, and DGX OS, an Ubuntu-based Linux; the EVO-X2 uses a Radeon GPU with ROCm or Vulkan and also runs Windows. If your tools require CUDA, the EVO-X2 isn't a fit; otherwise, compare measured throughput and current prices.

#Sources and verification as of November 18, 2026

Specs and prices were collected on November 18, 2026 from GMKtec's official stores, settings from AMD and Ollama documentation, and measurements from ServeTheHome and Tom's Hardware reviews; prices, drivers, and required kernel versions may change.

Did this guide help you?

Feedback, an error, or a clarification? Let us know—it improves the guide for everyone.

Prices in euros (€) are French market prices including VAT, as checked by BestLLMfor. US prices differ: the Amazon buttons show the current US price.