{"product_id":"amd-ryzen-ai-halo-ai-max-plus-395-128gb","title":"AMD Ryzen AI Halo | AI Max+ 395 | 128GB | 60 TFLOPS | Windows\/Linux","description":"\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eAMD Ryzen AI Max+ 395 Processor\u003c\/strong\u003e — Flagship Ryzen AI processor with 60 FP16 TFLOPS GPU performance and up to 50 TOPS NPU for local AI inference and development\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e128GB LPDDR5x Unified Memory\u003c\/strong\u003e — Large unified memory pool for running up to 200B parameter models locally without cloud dependency\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 3x Faster Than Apple M4 Pro\u003c\/strong\u003e — Outperforms Apple M4 Pro on image generation workloads including Stable Diffusion XL, Flux, and Hunyuan 3D\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 14% More Tokens\/Sec Than NVIDIA DGX Spark\u003c\/strong\u003e — Faster LLM inference vs DGX Spark on GPT OSS 120B, Qwen, and GLM models at a lower price point\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eWindows \u0026amp; Linux OS Support\u003c\/strong\u003e — Run AI workflows on either OS — an advantage over NVIDIA DGX Spark which supports Linux only\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 50 TOPS NPU\u003c\/strong\u003e — Dedicated neural processing unit for accelerated AI workloads alongside the GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePre-Configured AI Software Stack\u003c\/strong\u003e — Ships ready to build with AMD ROCm, Ollama, LM Studio, PyTorch, vLLM, and more\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAMD Ryzen AI Developer Center App\u003c\/strong\u003e — Central hub for playbooks, tools, software sync, and developer resources\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eThe AMD Ryzen AI Halo is AMD’s purpose-built local AI developer platform — designed to go from power-on to running AI models in minutes without cloud dependency or complex configuration. Powered by the Ryzen AI Max+ 395 processor with 128GB of LPDDR5x unified memory, it runs models up to 200B parameters locally, delivering predictable cost-per-token versus cloud API billing. AMD ROCm software provides class-leading generative AI performance with Day 0 model and framework support.\u003c\/p\u003e\n\u003cp\u003eIn independent testing, the Ryzen AI Halo delivers up to 14% more tokens per second than NVIDIA DGX Spark across LLM benchmarks — at $700 less. It outperforms Apple M4 Pro by up to 7.3× on AI image generation tasks including Flux, Stable Diffusion XL, and Hunyuan 3D. Over a 3-year modeled scenario, local inference on the Ryzen AI Halo costs up to 6× less than equivalent cloud API usage. Available in Windows 11 Pro and Linux OS configurations.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eIdeal For\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Developers \u0026amp; Researchers\u003c\/strong\u003e — Local LLM inference, fine-tuning, and model development without cloud costs\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eGenerative AI \u0026amp; Image Generation\u003c\/strong\u003e — Run Stable Diffusion XL, Flux, Hunyuan 3D, and ComfyUI workflows locally at full speed\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eLLM Inference at Scale\u003c\/strong\u003e — Support up to 200B parameter models on 128GB unified memory with AMD ROCm\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Agent Development\u003c\/strong\u003e — Real-time reasoning, persistent memory, and automation without token costs\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePrivacy-First AI Workloads\u003c\/strong\u003e — All inference runs locally — no data leaves the machine\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eVariant Options\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eWindows 11 Pro\u003c\/strong\u003e — AMD Ryzen AI Max+ 395, 128GB LPDDR5x, Windows 11 Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eLinux OS\u003c\/strong\u003e — AMD Ryzen AI Max+ 395, 128GB LPDDR5x, Linux OS\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eSpecifications\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eProcessor\u003c\/strong\u003e — AMD Ryzen AI Max+ 395\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory\u003c\/strong\u003e — 128GB LPDDR5x (unified CPU+GPU)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMax Model Size\u003c\/strong\u003e — Up to 200B parameters\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eGPU Performance\u003c\/strong\u003e — 60 FP16 TFLOPS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNPU Performance\u003c\/strong\u003e — Up to 50 TOPS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS Options\u003c\/strong\u003e — Windows 11 Pro \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSoftware\u003c\/strong\u003e — AMD ROCm, Ollama, LM Studio, PyTorch, vLLM, LoRA, QLoRA, ComfyUI\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"AMD","offers":[{"title":"Windows 11 Pro","offer_id":52189381493057,"sku":null,"price":3999.99,"currency_code":"USD","in_stock":false},{"title":"Linux OS","offer_id":52189381525825,"sku":null,"price":3999.99,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0954\/5524\/8705\/files\/AMDRyzen_AIHalo.webp?v=1788976368","url":"https:\/\/aaawave.com\/products\/amd-ryzen-ai-halo-ai-max-plus-395-128gb","provider":"AAAWave","version":"1.0","type":"link"}