Key Takeaways
- The A9 Max runs Home Assistant, Frigate, Whisper, and a 7B–13B local LLM on one box with headroom
- Ryzen AI 9 HX 370: 12 cores/24 threads, Radeon 890M iGPU, up to 128 GB DDR5 (two user-replaceable SO-DIMMs)
- Local-LLM speed comes from the iGPU and RAM bandwidth — the 50-TOPS NPU accelerates vision, not chat models
- At ~$1,099–1,299 (July 2026, volatile) it is roughly double a Beelink SER8
- Buy it for the 128 GB ceiling, Wi-Fi 7, and vision headroom; otherwise the SER8 is better value
- Made in China — factor 2026 US/EU import measures into landed cost (see trade note)
Verdict — Who Should Buy It
Buy the GEEKOM A9 Max if you want a single mini PC that runs a local-AI smart home with years of headroom and you accept a premium price. Its 12-core Ryzen AI 9 HX 370, Radeon 890M iGPU, and 128 GB RAM ceiling make it the most future-proof box in this set. If your goal is the cheapest capable machine, stop here and read the SER8 review — the A9 Max is overkill for a hub plus a 7B model.
Its single strongest use case is an always-on home server that runs Home Assistant, Frigate, and a mid-size local LLM at once without you thinking about RAM. The Wi-Fi 7 radio, dual 2.5GbE, and two USB4 ports also make it a capable general workstation between smart-home duties.
Specifications
All specs below were verified against GEEKOM and independent review sources in July 2026. A separate "2026 Edition" SKU ships the Ryzen AI 9 HX 470 (86 TOPS total) at a higher price; the table reflects the mainstream HX 370 unit.
- No discrete GPU: all AI inference runs on the CPU and Radeon 890M iGPU sharing system RAM.
- The two SO-DIMM slots are user-replaceable — you can start at 32 GB and move to 64 GB or 128 GB later.
| Spec | GEEKOM A9 Max (HX 370) |
|---|---|
| CPU | AMD Ryzen AI 9 HX 370 (Zen 5, 4 nm) |
| Cores / threads | 12 cores / 24 threads, up to 5.1 GHz |
| iGPU | AMD Radeon 890M — 16 CU, RDNA 3.5 |
| NPU | XDNA 2, 50 TOPS (80 TOPS platform total) |
| RAM | 32 GB DDR5-5600 as tested; 2 SO-DIMM slots; up to 128 GB (user-replaceable) |
| Storage | 1–2 TB NVMe; 2× M.2 PCIe 4.0; up to 8 TB |
| Ports | 2× USB4 (40 Gbps), 5× USB-A 10 Gbps, 1× USB 2.0, 2× HDMI 2.1, SD reader, 3.5 mm |
| Networking | 2× 2.5GbE, Wi-Fi 7, Bluetooth 5.4 |
| TDP | ~54 W sustained (PL1), 65 W boost (PL2) |
| Dimensions | 135 × 132 × 46 mm |
| OS | Windows 11 Pro (Linux/Proxmox install supported) |
| Price (indicative) | ~$1,099–1,299 (July 2026 — volatile, check current price) |
Local AI & LLM Performance
With 32 GB of RAM the A9 Max comfortably runs a 7B–8B model on Ollama and fits a 13B–14B model at 4-bit with room for context — all figures estimated from the verified hardware, not a measured benchmark. Moving to 64 GB opens 30B-class models, and the 128 GB ceiling lets a 70B model load at 4-bit, though large models are limited by memory bandwidth (dual-channel DDR5-5600, no dedicated VRAM) and are usable for experimentation rather than fast serving.
- Ollama, LM Studio, and llama.cpp all run well; the Radeon 890M is used through Vulkan or ROCm backends.
- The 50-TOPS NPU accelerates vision workloads such as Frigate object detection — it does not speed up local LLMs, which the runtimes place on the CPU/iGPU.
- Home Assistant plus Ollama plus Whisper plus Frigate fit together on 32 GB; add RAM if you want a larger model alongside camera recording.
- Sustained ~54 W under load keeps always-on running cost modest; see Ollama on Home Assistant to wire the model in.
- For VRAM and quantization depth across boxes, see the cross-cluster local LLM hardware guide.
Pros & Cons
The A9 Max trades price for headroom. Balanced view below.
- Pros
- 128 GB RAM ceiling — the largest in this set, so it fits the biggest local models
- 12-core Ryzen AI 9 HX 370 with Radeon 890M — strong iGPU for a mini PC
- User-replaceable SO-DIMM RAM and dual M.2 slots — you can upgrade later
- Wi-Fi 7, dual 2.5GbE, two USB4 ports — well connected for a home server
- Runs cool and quiet at ~54 W sustained for an always-on box
- Cons
- Expensive — roughly $1,099–1,299, about double a Beelink SER8
- The 50-TOPS NPU does not accelerate local LLMs (a common misconception)
- iGPU + shared-memory design is bandwidth-limited for very large models
- Overkill if you only run Home Assistant plus a 7B model
Buyer Context: Tariffs & Availability (2026)
The A9 Max is manufactured in China, so its landed price reflects 2026 trade measures — a reason to treat any price as a moving target. The facts below are buyer context, not editorial opinion.
- US: Section 301 tariffs on Chinese electronics remain in force in 2026; the separate 2025 "IEEPA" tariffs were struck down by the Supreme Court in February 2026 and replaced by a temporary, capped Section 122 tariff. The sub-$800 duty-free "de minimis" exemption for direct imports has also ended.
- EU (affects DE/FR): there is no broad EU tariff on finished mini PCs, but from July 2026 the €150 duty-free threshold on low-value direct-from-China parcels was removed and a small per-parcel handling fee added.
- Assumption (macro trend, not a per-product fact): redirected Chinese export capacity has kept availability of these brands high in the EU and US, which broadly supports competitive pricing.
- Net effect: verify the current price at the retailer before buying — the figures in this review are indicative and date-stamped July 2026.
Where to Buy & Current Price
Prices move week to week, so check the live price rather than trusting a fixed figure. As of July 2026 the mainstream HX 370 / 32 GB / 2 TB configuration sits around $1,099–1,299, with the "2026 Edition" HX 470 SKU higher.
- Confirm the exact SKU (HX 370 vs HX 470, RAM and storage capacity) before ordering — pricing and specs differ.
Alternatives to Consider
If the A9 Max is more than you need, three cheaper boxes cover most of the same jobs.
- Beelink SER8 — the value pick: Ryzen 7 8845HS, 32 GB, ~$650, runs a 7B model comfortably
- Minisforum UM890 Pro — adds an OCuLink port for an external GPU if you want faster large-model inference later
- Beelink EQ14 — budget Intel N150 box for Home Assistant plus a tiny model
- GMKtec G3 Plus — another budget N150 option with upgradeable RAM
- Still comparing? Start from the best mini PCs for Home Assistant + local AI roundup.
Frequently Asked Questions
Can the GEEKOM A9 Max run local LLMs?
Yes. With 32 GB of RAM it comfortably runs a 7B–8B model on Ollama and fits a 13B–14B model at 4-bit quantization with room for context. This is estimated from its verified hardware rather than a fixed benchmark, because speed depends on the model, quantization, and backend.
How big a model fits in its RAM?
At the 32 GB tested capacity, up to a 13B–14B model at 4-bit is realistic. Upgrading to 64 GB opens 30B-class models, and the 128 GB ceiling lets a 70B model load at 4-bit — though very large models run slowly because the iGPU shares system memory and has no dedicated VRAM.
Does the NPU make local LLMs faster?
No. The 50-TOPS NPU accelerates vision and some Windows AI features, but mainstream local-LLM runtimes such as Ollama and llama.cpp run the model on the CPU and Radeon 890M iGPU. Treat the NPU as a benefit for Frigate camera detection, not for chat-model speed.
Is the A9 Max good for Home Assistant and always-on use?
Yes. It runs Home Assistant, Ollama, Whisper, and Frigate together with headroom, and its ~54 W sustained draw keeps always-on running cost modest. Its dual 2.5GbE and Wi-Fi 7 also suit a wired home-server role.
Is the RAM upgradeable?
Yes. The A9 Max uses two standard DDR5 SO-DIMM slots that are user-replaceable, so you can start at 32 GB and move to 64 GB or 128 GB later. This is a genuine advantage over mini PCs with soldered memory.
How much power does it use?
It runs at roughly 54 W sustained under load and much less at idle, so leaving it on continuously is inexpensive. The exact figure varies with the model you run and the power profile you select in the BIOS.
Is the A9 Max worth it over a Beelink SER8?
Only if you want the extra headroom. The SER8 runs Home Assistant plus a 7B model for about half the price. The A9 Max is worth the premium if you need the 128 GB RAM ceiling, Wi-Fi 7, or vision headroom for the years ahead.
Where is the GEEKOM A9 Max made, and does that affect price?
It is manufactured in China. In 2026 US import measures (Section 301 tariffs, the end of the sub-$800 de minimis exemption) and the EU removal of the €150 low-value parcel exemption can affect landed cost, so check the current retailer price rather than relying on a fixed number.