UNIT · OTHER · DESKTOP
128 GB UNIFIEDworkstationReviewed July 2026

GMKtec EVO-X3

No editorial image yet — generic vendor mark shown. Credentials in spec table below.

The EVO-X3 is GMKtec's second-generation Strix Halo mini-PC, launched globally on July 6, 2026 around the same Ryzen AI Max+ 395 (16 Zen 5 cores, Radeon 8060S, up to 126 platform TOPS) that powered the EVO-X2. Its 128 GB of LPDDR5X-8000 is soldered and non-upgradeable, with up to 96 GB allocatable as VRAM; GMKtec claims support for models up to Qwen3-235B. The PS4-sized chassis adds what the EVO-X2 lacked — a PCIe Gen4 x4 OCuLink port for eGPU expansion — alongside USB4 (40 Gbps, 100 W PD), dual M.2 Gen4 slots for up to 16 TB of storage, 2.5GbE, Wi-Fi 7, a 140 W peak performance mode, and GMKtec's pre-installed Claw local-AI launcher. Launch pricing is $3,600 for 128 GB/2 TB and $3,849 for 4 TB — roughly double the EVO-X2's launch price for the same memory and storage.

Released 2026·256 GB/s memory bandwidth
▼ CHECK CURRENT PRICE· 1 retailer
GMKtec EVO-X3

Affiliate disclosure: as an Amazon Associate and partner of other retailers, we earn from qualifying purchases. The verdict on this page is our editorial opinion; affiliate links never influence what we recommend.

RUNLOCALAI SCORE
See full leaderboard →
106/ 1000
DD-tier
Estimated
Throughput
59/ 500
VRAM-fit
0/ 200
Ecosystem
80/ 200
Efficiency
12/ 100

Sub-scores sum to 151 / 1000. Headline = 151 × 0.70 (Estimated-confidence discount) = 106. This is an algorithmic performance-tier score — distinct from, and often lower than, the editorial “Our verdict” below, which weighs value and real-world fit (especially for hardware we haven’t measured yet). How scoring works →

Extrapolated from 256 GB/s bandwidth — 20.5 tok/s estimated. No measured benchmarks yet.

Plain-English: Doesn't fit modern chat models usefully — vision models won't fit.

7B chat
Doesn't fit
14B chat
Doesn't fit
32B chat
Doesn't fit
70B chat
Doesn't fit
Coding agent
Doesn't fit
Vision (≤8B VLM)
Doesn't fit
Long context (32K)
Doesn't fit
Comfortable — fits with headroom
~Tight — works, no slack
Marginal — needs aggressive quant
Doesn't fit usefully

Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.

BLK · VERDICT

Our verdict

OP · Eruo Fredoline|VERIFIED JUL 10, 2026
unrated

Positioning

Judge the EVO-X3 on what the extra money buys, because the silicon has not changed: this is the same Ryzen AI Max+ 395 and 128 GB of LPDDR5X-8000 as the EVO-X2, now at $3,600 — double that machine's launch price for the identical memory/storage configuration. That delta is the memory supply crunch showing up on a price tag, not added performance. What is genuinely new is the OCuLink Gen4 x4 port, and it matters: it is the cleanest path in this class to bolt on a discrete GPU for prefill-heavy work, the exact scenario where StorageReview measured this silicon trailing the DGX Spark by up to 8.8x. Against AMD's own Ryzen AI Halo at $3,999, the EVO-X3 is $400 cheaper and adds OCuLink, but gives up 10GbE (2.5GbE here), the first-party dual-OS developer images, and Micro Center-backed support — for most US buyers the Halo is the safer spend. A used M2 Ultra Mac Studio remains the bandwidth play at 800 GB/s versus 256 GB/s; decode speed on large dense models will favor it decisively, though you lose x86, ROCm, and the eGPU option. Buy the EVO-X3 if you specifically want OCuLink expansion or cannot reach a Micro Center. Skip it if you can still find EVO-X2 stock near its original price — it is the same computer — or if $3,600 feels like Spark-adjacent money, since base Spark-class systems sell near $4,000.

BLK · OVERVIEW

Overview

The EVO-X3 is GMKtec's second-generation Strix Halo mini-PC, launched globally on July 6, 2026 around the same Ryzen AI Max+ 395 (16 Zen 5 cores, Radeon 8060S, up to 126 platform TOPS) that powered the EVO-X2. Its 128 GB of LPDDR5X-8000 is soldered and non-upgradeable, with up to 96 GB allocatable as VRAM; GMKtec claims support for models up to Qwen3-235B. The PS4-sized chassis adds what the EVO-X2 lacked — a PCIe Gen4 x4 OCuLink port for eGPU expansion — alongside USB4 (40 Gbps, 100 W PD), dual M.2 Gen4 slots for up to 16 TB of storage, 2.5GbE, Wi-Fi 7, a 140 W peak performance mode, and GMKtec's pre-installed Claw local-AI launcher. Launch pricing is $3,600 for 128 GB/2 TB and $3,849 for 4 TB — roughly double the EVO-X2's launch price for the same memory and storage.

Retailers we'd check:Amazon

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

BLK · SPECS

Specs

System RAM (typical)128 GB
Power draw (peak)140 W
Released2026
MSRP$3600
Backends
ROCm
Vulkan

Models that fit

Open-weight models small enough to run on GMKtec EVO-X3 with usable context.

Compare alternatives

Hardware worth comparing

The closest alternatives by price, memory bandwidth, and form factor, plus a step up and down — so you can frame the buying decision against real options.

Frequently asked

Does GMKtec EVO-X3 support CUDA?

No — GMKtec EVO-X3 is an AMD card. Use ROCm (Linux) or the Vulkan backend in llama.cpp instead. CUDA-only tools won't work.

Where next?

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.