Beelink GTR9 Pro (Ryzen AI Max+ 395, 128GB)
$1,899 – $1,999
The best-connected 128GB Strix Halo box. Same Ryzen AI Max+ 395 silicon and 128GB LPDDR5X-8000 as the rest, but the GTR9 Pro adds dual 10GbE and dual USB4 — the IO you want for clustering boxes or pulling models off a fast NAS. A vapor-chamber cooler keeps sustained ~120W inference quiet. Watch for driver-dependent 10GbE instability under heavy GPU load.
Affiliate links — We earn a commission on qualifying purchases at no cost to you.
Specifications
| APU | AMD Ryzen AI Max+ 395 (16C/32T, Zen 5) |
| GPU | Radeon 8060S (40 CU, RDNA 3.5) |
| NPU | 50 TOPS (XDNA 2) |
| Unified Memory | 128GB LPDDR5X-8000 |
| Memory Bandwidth | ~256–273 GB/s |
| Storage | 2TB NVMe (dual M.2 2280, up to 16TB) |
| Networking | Dual 10GbE (Intel E610), Wi-Fi 7 |
| I/O | 2× USB4 (40Gbps), HDMI 2.1, DP 2.1 |
Pros
- Dual 10GbE — rare at this size; fast model/dataset transfer to a NAS or cluster
- Dual USB4 + vapor-chamber cooling keep sustained ~120W inference quiet (~36–41 dBA)
- 128GB unified runs Q4 70B-class models at a price no consumer dGPU touches
Cons
- Reported 10GbE NIC instability/BSOD under heavy GPU load — driver-dependent
- ~256–273 GB/s bandwidth ceiling — 70B is usable but not GPU-fast
- 128GB soldered, non-upgradable — buy max config or nothing
Related Articles
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.
How to Unlock the Full 128GB as VRAM on a Ryzen AI Max+ 395 (Strix Halo): BIOS + Linux GTT Guide
You bought a 128GB Strix Halo box and the GPU only sees ~16GB. Here's the fix: Windows caps GPU-allocatable memory at 96GB via the BIOS UMA frame buffer, but Linux with the amdttm GTT kernel params reaches ~110–120GB — and the winning move is counterintuitive.
How Fast Is Strix Halo, Really? Real Tokens-Per-Second for Local LLMs (Dense vs MoE)
On the Ryzen AI Max+ 395, a dense 70B model crawls at ~5 tok/s — but a 30B MoE model hits 70–100 tok/s on the same box. Here's the full tokens-per-second table by model size, why memory bandwidth caps it, and why MoE changes the whole buying decision.
GMKtec EVO-X2 Review (2026): The 128GB Ryzen AI Max+ 395 Mini PC That Runs 70B Models — Real Benchmarks & Who Should Buy
The GMKtec EVO-X2 is a ~$2,000 128GB Strix Halo box that holds a 4-bit 70B model and runs it at 5–10 tok/s (7B at 50–80). Real per-model benchmarks, thermals, the ROCm reality, and whether it beats the Framework Desktop, Beelink GTR9 Pro, and $3,999 DGX Spark.
Related Products
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. This helps support our independent reviews.