{"product_id":"beelink-ser9-pro-amd-pro-ryzen-ai-9-hx-370-openclaw-038-local-llm-pre-installed","title":"Beelink SER9 PRO AMD Pro Ryzen™ AI 9 HX 370 (OpenClaw \u0026 Local LLM Pre-installed)","description":"\u003cp\u003eThe Beelink SER9 PRO pairs AMD’s Ryzen AI 9 HX 370 (12 Zen 5 cores, a Radeon 890M iGPU, and an XDNA 2 NPU good for 80 AI TOPS) with OpenClaw and local LLM tooling pre-installed. It sits in the same compact 135 x 135 x 44.7mm chassis as Beelink’s other SER-series machines. It is for developers and AI enthusiasts who want on-device model inference in a machine small enough to disappear on a desk, not a full tower workstation.\u003c\/p\u003e\u003ch2\u003eWho it's for\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eDevelopers building agentic coding workflows with OpenClaw who want no API latency, no per-token cost, and no code or prompts sent to a third party\u003c\/li\u003e\n\u003cli\u003eRunning mid-size quantized open-weight models locally with Ollama or llama.cpp\u003c\/li\u003e\n\u003cli\u003eMulti-monitor productivity setups with up to triple 4K displays\u003c\/li\u003e\n\u003cli\u003eGeneral-purpose use as well, including creative work and light gaming on the 890M iGPU\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eKey features\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eAMD Ryzen™ AI 9 HX 370, 12 cores, 24 threads:\u003c\/strong\u003e Zen 5 cores boost up to 5.1GHz with 36MB of combined L2+L3 cache, for compiling, running local models, and heavy multitasking at once.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAMD Radeon™ 890M, RDNA 3.5, 16 compute units:\u003c\/strong\u003e Running at up to 2900MHz, it is widely regarded as the fastest integrated GPU class in a mini PC, able to handle GPU-accelerated inference alongside light gaming.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e80 AI TOPS via XDNA 2 NPU:\u003c\/strong\u003e A dedicated NPU gives OpenClaw and local inference tooling like Ollama or llama.cpp on-device throughput for quantized models instead of depending on a cloud connection.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e32GB LPDDR5X 7500MHz memory:\u003c\/strong\u003e High-bandwidth soldered memory keeps model loading and inference responsive, sized for mid-size quantized open-weight models alongside your normal workload.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eDual PCIe 4.0 NVMe storage, up to 8TB:\u003c\/strong\u003e Two M.2 2280 PCIe 4.0 x4 slots support up to 8TB combined, and the retail unit includes a 1TB or 2TB Crucial SSD, leaving room for multiple model checkpoints.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eTriple 4K display output:\u003c\/strong\u003e DisplayPort 1.4 (4K@240Hz), HDMI 2.1 (4K@240Hz), and USB4 (40Gbps\/TB3\/PD\/DP1.4) together support up to triple 4K displays.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e32dB near-silent cooling:\u003c\/strong\u003e Efficient bottom-intake airflow keeps the chip stable at 65W TDP with very low fan noise, even during sustained AI inference.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI-enhanced voice pickup and dual speakers:\u003c\/strong\u003e A built-in microphone processed through an AI chip gives 360° barrier-free voice recognition within 5 meters, with dual speakers for calls and media.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eSpecifications\u003c\/h2\u003e\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003eAMD Ryzen™ AI 9 HX 370, 12C\/24T Zen 5, up to 5.1GHz boost, 36MB cache\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU\u003c\/td\u003e\n\u003ctd\u003eAMD Radeon™ 890M, 16 CUs, up to 2900MHz, RDNA 3.5\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI\u003c\/td\u003e\n\u003ctd\u003eXDNA 2 NPU, 80 AI TOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e32GB LPDDR5X 7500MHz (soldered)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003eDual M.2 2280 PCIe 4.0 x4 slots, up to 8TB combined; 1TB or 2TB Crucial SSD included\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay outputs\u003c\/td\u003e\n\u003ctd\u003eDisplayPort 1.4 (4K@240Hz), HDMI 2.1 (4K@240Hz), USB4 (40Gbps\/TB3\/PD\/DP1.4), triple 4K support\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNetworking\u003c\/td\u003e\n\u003ctd\u003eWi-Fi, Bluetooth\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCooling\u003c\/td\u003e\n\u003ctd\u003e~32dB near-silent operation, 65W TDP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAudio\u003c\/td\u003e\n\u003ctd\u003eAI-enhanced 360° 5-meter microphone pickup, dual speakers\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDesign\u003c\/td\u003e\n\u003ctd\u003eDust-proof bottom mesh filter, 135 x 135 x 44.7mm chassis\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSoftware\u003c\/td\u003e\n\u003ctd\u003eOpenClaw and local LLM tooling pre-installed; Windows 11 Pro or Ubuntu\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\u003ch2\u003eGood to know\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eThe 80 TOPS NPU makes local inference practical for smaller quantized models run entirely on-device.\u003c\/li\u003e\n\u003cli\u003eFor the largest local models, 70B-class and above, the GTR9 Pro’s 128GB unified memory platform is the better fit.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eChoose the SER9 PRO for mid-size quantized models and agentic coding workloads in a quiet, compact box. Step up to the GTR9 Pro only if you need the largest models.\u003c\/p\u003e","brand":"Beelink","offers":[{"title":"32GB LPDDR5x memory (soldered) + 1TB SSD \/ Ubuntu","offer_id":58232531550590,"sku":"BL-SER9PRO-HX370-OC-UK-32GB-1TB-UBUNTU","price":1169.0,"currency_code":"USD","in_stock":true},{"title":"32GB LPDDR5x memory (soldered) + 1TB SSD \/ Ubuntu + Windows","offer_id":58232531583358,"sku":"BL-SER9PRO-HX370-OC-UK-32GB-1TB-WIN-UBUNTU","price":1189.0,"currency_code":"USD","in_stock":true},{"title":"32GB LPDDR5x memory (soldered) + 2TB SSD \/ Ubuntu","offer_id":58232531616126,"sku":"BL-SER9PRO-HX370-OC-UK-32GB-2TB-UBUNTU","price":1389.0,"currency_code":"USD","in_stock":true},{"title":"32GB LPDDR5x memory (soldered) + 2TB SSD \/ Ubuntu + Windows","offer_id":58232531648894,"sku":"BL-SER9PRO-HX370-OC-UK-32GB-2TB-WIN-UBUNTU","price":1369.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/b58ce7b99582c961375527c3c6b27ebb_c9419f3e-ab07-47d7-be2d-9c5cbed745c8.png?v=1792093973","url":"https:\/\/computahardware.net\/products\/beelink-ser9-pro-amd-pro-ryzen-ai-9-hx-370-openclaw-038-local-llm-pre-installed","provider":"ComputaHardware","version":"1.0","type":"link"}