Beelink GTR9 Pro (Ryzen AI Max+ 395, 128GB)
$4,349
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 inference quiet — 125–128W at 39–41 dBA on gpt-oss 120B (ServeTheHome)
- 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
192GB vs 128GB Unified Memory: What the Extra 64GB Actually Buys You
IFA 2026 filled the feeds with 192GB Gorgon Halo mini PCs. Capacity went up 50%; bandwidth went up about 7%. That asymmetry decides the whole purchase — here is the model-by-model list of what only 192GB runs, and why most buyers should still buy 128GB today.
Can You Fine-Tune an LLM on a 128GB Mini PC? (And Which Box to Buy in 2026)
LoRA and QLoRA on 20–30B models are practical on 128GB of unified memory; full fine-tunes stop near 12B; dense 70B training doesn't happen on any box in this class. Fine-tuning is the one local-AI workload where the software stack — not memory bandwidth — decides which machine you buy. Here's the capability table, the CUDA tax, and the cloud break-even.
Strix Halo Memory Bandwidth: Why 256 GB/s Isn't 256 GB/s (2026)
AMD's Ryzen AI Max+ 395 is rated 256 GB/s. Real sustained bandwidth is around 215 GB/s — about 84% of spec. Here's where the missing 40 GB/s goes, why 32MB of Infinity Cache doesn't rescue it, and how to turn GB/s into a tokens-per-second estimate before you buy.
Best Mini PC for a Local Coding Agent in 2026 — Why Prefill, Not Tokens/Sec, Decides Your Box
A coding agent re-sends your whole repo context every single turn, which makes it a prefill-bound workload. That flips the buying logic: ~1,700 tok/s prompt processing on a GB10 box vs ~340 tok/s on Strix Halo, while generation is a near-tie. Here's the per-budget verdict, the memory math, and the boxes to skip — with the caveat that the 2026 DRAM spike has narrowed the price gap to about $1,250.
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.