NVIDIA DGX Spark (GB10 Grace Blackwell) vs GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB) for AI
A head-to-head comparison of specs, pricing, and real-world AI performance to help you pick the right hardware.
Disclosure: Some links on this page are affiliate links. We may earn a commission if you make a purchase — at no extra cost to you.
Quick Verdict
The GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB) offers better value at a lower price point. Unless you specifically need the NVIDIA DGX Spark (GB10 Grace Blackwell)'s features, the GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB) is the smarter buy for most AI use cases.
NVIDIA DGX Spark (GB10 Grace Blackwell)
$4,699+
NVIDIA's desktop AI supercomputer, and the CUDA-native answer to the Strix Halo boxes. The GB10 Grace Blackwell superchip pairs a 20-core Arm CPU with a Blackwell GPU and 128GB of coherent unified memory, with a 200GbE ConnectX-7 NIC so two units cluster to run 405B-class models. The headline '1 PFLOP FP4' is sparse — dense compute is roughly half (≈RTX 5070-class) — and at 273 GB/s, memory bandwidth is the real ceiling. You're buying CUDA + capacity, not bandwidth.
GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB)
$3,399 – $3,499
The flagship local-AI mini PC. AMD's Ryzen AI Max+ 395 'Strix Halo' pairs a 16-core Zen 5 CPU with a Radeon 8060S iGPU and 128GB of LPDDR5X-8000 unified memory — up to 96GB assignable as VRAM, enough to load 70B-class models that won't fit on any consumer GPU. The catch is bandwidth: ~215 GB/s real, so dense 70B runs at single-digit tokens/sec. Buy it for capacity, not raw speed.
Specs Comparison
| Spec | NVIDIA DGX Spark (GB10 Grace Blackwell) | GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB) |
|---|---|---|
| Price | $4,699+ | $3,399 – $3,499 |
| Chip | GB10 Grace Blackwell Superchip | — |
| CPU | 20-core Arm (10× Cortex-X925 + 10× A725) | — |
| GPU | Blackwell (5th-gen Tensor Cores), CUDA-native | Radeon 8060S (40 CU, RDNA 3.5) |
| AI Performance | Up to 1 PFLOP FP4 sparse (~500 TFLOPS dense) | — |
| Unified Memory | 128GB LPDDR5X | 128GB LPDDR5X-8000 (up to 96GB GPU-allocatable) |
| Memory Bandwidth | 273 GB/s | 256 GB/s theoretical (~215 GB/s real) |
| Networking | ConnectX-7 200GbE (2-unit clustering), 10GbE RJ-45 | 2.5GbE, Wi-Fi 7 |
| Storage | 4TB NVMe (self-encrypting) | 2TB NVMe (dual M.2 2280, up to 16TB) |
| OS | NVIDIA DGX OS (Ubuntu-based) | — |
| APU | — | AMD Ryzen AI Max+ 395 (16C/32T, Zen 5) |
| NPU | — | 50 TOPS (XDNA 2) |
| I/O | — | 2× USB4, HDMI 2.1, DP 1.4 |
NVIDIA DGX Spark (GB10 Grace Blackwell)
Pros
- +CUDA-native + full NVIDIA/DGX software stack — best dev ergonomics for AI work
- +128GB unified in a 1.2kg box; 2-unit 200GbE stacking reaches 405B-class locally
- +Drop-in compatibility with the datacenter toolchain
Cons
- -273 GB/s bandwidth is low for the price — token throughput lags Apple Ultra and GPUs
- -Headline '1 PFLOP FP4' is sparse-only; dense compute ~5070-class, not datacenter-class
- -NVIDIA raised the official price from $3,999 to $4,699 (2026-02-27) on memory supply; stock is thin
GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB)
Pros
- +128GB unified memory (96GB allocatable) loads 70B-class models no 24–32GB dGPU can hold
- +256-bit LPDDR5X-8000 is ~2× a normal desktop APU — the reason it produces usable tokens/sec
- +Quiet, cool, dual-M.2 expandable — a practical always-on local inference appliance
Cons
- -~215 GB/s is far below a discrete GPU (800–1000 GB/s) — dense 70B is single-digit tok/s
- -Memory is soldered — you must buy the 128GB SKU up front; no upgrade path
- -2.5GbE only (no 10GbE/OCuLink); ROCm/Linux GPU-compute on Strix Halo still rough vs CUDA
Where to Buy
Related Articles
guide
Can You Cluster Two Mini PCs to Run Bigger Local LLMs? (2026 Reality Check)
AMD published a four-node Framework Desktop cluster running a trillion-parameter model, and two DGX Sparks pool 256GB over a single cable. Here's when a second box actually helps, when it makes things slower, and which mini PC to buy if clustering is on your roadmap.
guide
Why Local-AI Mini PC Prices Doubled in 2026 — And Whether to Buy Now or Wait
The GMKtec EVO-X2 went from ~$1,999 to ~$3,399. NVIDIA repriced the DGX Spark from $3,999 to $4,699 on 2026-02-27, citing memory supply. Here's the SKU-by-SKU price damage, why DRAM did it, and why waiting is the wrong call — with TrendForce's own 2027 forecast as the evidence.
guide
Beelink GTR9 Pro Review (2026): The 128GB Strix Halo Box With Dual 10GbE — Real Local-LLM Benchmarks & Who Should Buy
The Beelink GTR9 Pro is a ~$1,899–$1,999 128GB Ryzen AI Max+ 395 mini PC that runs GPT-OSS 120B at ~31 tok/s (~120W) but a dense 70B at only ~5 tok/s. Its real hook is dual 10GbE — plus a real caveat: reported 10GbE instability under heavy GPU load. Benchmarks, thermals, and how it stacks up against the EVO-X2, Framework Desktop, and DGX Spark.