{"product_id":"roc-rk3576-pc-low-power-large-model-mini-computer","title":"ROC-RK3576-PC Low-Power Large Model Mini Computer - AIOT Rockchip RK3576, 4K@120fps, Credit card size, The private deployment of large models Docker","description":"\u003ch1 style=\"text-align: center;\"\u003e\n\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003c\/span\u003e\u003c\/b\u003eROC-RK3576-PC Low-Power Large Model Mini Computer\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003c\/span\u003e\u003c\/b\u003e\n\u003c\/h1\u003e\n\u003chr\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cspan style=\"font-size: 18px;\"\u003eQuick Start\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan style=\"font-size: 18px;\"\u003eTips\u003c\/span\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cspan style=\"color: #3598db;\"\u003e\u003ca href=\"https:\/\/www.youyeetoo.com\/products\/ec-r3576pc-fd-embedded-large-model-computer\" style=\"color: #3598db;\" target=\"_blank\" rel=\"noopener\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eIf you need the whole machine with metal case, you can choose EC-R3576PC FD, click here.\u003c\/span\u003e\u003c\/a\u003e\u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003e\n\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003cbr\u003eIntroduction\u003c\/span\u003e\u003c\/b\u003e\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e \u003c\/span\u003e\u003c\/b\u003e\n\u003c\/h2\u003e\n\u003chr\u003e\n\u003cp\u003e\u003cspan data-font-family=\"default\" style=\"font-size: 18px;\"\u003eROC-RK3576-PC - Low-Power Large Model Mini Computer\u003cbr\u003ePowered by the Rockchip RK3576, an octa-core 64-bit AIOT processor, ROC-RK3576-PC features a big.LITTLE architecture (4×A72 +4×A53) and an advanced lithography process to deliver high performance while maintaining low power consumption. It is equipped with an ARM Mali G52 MC3 GPU and a 6 TOPS NPU, supporting the private deployment of ultra-large parameter models under the Transformer architecture. It is compatible with various deep learning frameworks, custom operator development, and Docker container management technology. With an external watchdog,\u003cbr\u003eit ensures industrial-grade reliability, making it an excellent choice for AI applications requiring local deployment.\u003c\/span\u003e\u003c\/p\u003e\n\u003ch2\u003e\n\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003cbr\u003eFeatures\u003c\/span\u003e\u003c\/b\u003e\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e \u003c\/span\u003e\u003c\/b\u003e\n\u003c\/h2\u003e\n\u003chr\u003e\n\u003col\u003e\n\u003cli\u003e\u003cspan data-font-family=\"default\" style=\"font-size: 18px;\"\u003e6 TOPS, 4K@120FPS, Rockchip RK3576,  UFS2.0\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan data-font-family=\"default\" style=\"font-size: 18px;\"\u003esupports LLMs and traditional CNN neural networks \u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ol\u003e\n\u003ch2\u003e\n\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003cbr\u003eShipping List\u003c\/span\u003e\u003c\/b\u003e\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e \u003c\/span\u003e\u003c\/b\u003e\n\u003c\/h2\u003e\n\u003chr\u003e\n\u003cp\u003e\u003cspan data-font-family=\"default\" style=\"font-size: 18px;\"\u003e1x \u003cspan\u003eROC-RK3576-PC\u003c\/span\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003ch2\u003e\n\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003cbr\u003eApplications\u003c\/span\u003e\u003c\/b\u003e\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e \u003c\/span\u003e\u003c\/b\u003e\n\u003c\/h2\u003e\n\u003chr\u003e\n\u003cp\u003e\u003cspan data-font-family=\"default\" style=\"font-size: 18px;\"\u003eLarge-Model Computer, AI Edge kit\u003c\/span\u003e\u003c\/p\u003e\n\u003ch2\u003e\n\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003cbr\u003eSpecification\u003c\/span\u003e\u003c\/b\u003e\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e \u003c\/span\u003e\u003c\/b\u003e\n\u003c\/h2\u003e\n\u003chr\u003e\n\u003ctable class=\"new_param_table\" border=\"1\" style=\"width: 100%;\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"15\" class=\"new_param_left_title\" style=\"width: 13.875%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eBasic Specifications\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_left\" rowspan=\"2\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eSOC\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eRockchip RK3576\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eOcta-core 64-bit processor (4×A72 + 4×A53), up to 2.2GHz\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eGPU\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eG52 MC3 @ 1GHz, supporting OpenGL ES 1.1\/2.0\/3.2, OpenCL 2.0, Vulkan 1.1\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eBuilt-in high-performance 2D acceleration hardware\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eNPU\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e6 TOPS NPU, supporting INT4\/8\/16\/FP16\/BF16\/TF32 mixed operations\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eVPU\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eDecoding: 8K@30fps\/4K@120fps: H.265\/HEVC, VP9, AVS2, AV1, 4K@60fps: H.264\/AVC\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eEncoding: 4K@60fps: H.265\/HEVC, H.264\/AVC\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eRAM\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eLPDDR4\/LPDDR4x (4GB\/8GB optional)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eStorage\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eeMMC (16GB\/32GB\/64GB\/128GB\/256GB optional), UFS2.0 (optional)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\n\u003cspan style=\"font-size: 18px;\"\u003eStorage\u003c\/span\u003e\u003cbr\u003e\u003cspan style=\"font-size: 18px;\"\u003eExpansion\u003c\/span\u003e\n\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * M.2 (2242 PCIe NVMe\/SATA SSD expansion ), 1 * TF card slot\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003ePower\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eDC 12V (5.5mm * 2.1mm, 12V~24V wide input voltage)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eOS\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eAndroid14, Linux OS, and Buildroot+QT\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\n\u003cspan style=\"font-size: 18px;\"\u003eSoftware\u003c\/span\u003e\u003cbr\u003e\u003cspan style=\"font-size: 18px;\"\u003eSupport\u003c\/span\u003e\n\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e・ The private deployment of ultra-large-scale parameter models under the\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eTransformer architecture, such as Gemma-2B, LlaMa2-7B, ChatGLM3-6B, Qwen1.5-1.8B, and more.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e・ Traditional network architectures such as CNN, RNN, and LSTM;\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003ea variety of deep learning frameworks including TensorFlow, PyTorch, MXNet, PaddlePaddle, ONNX and Darknet.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e・ Custom operator development.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e・ Docker container management technology.\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\n\u003cspan style=\"font-size: 18px;\"\u003ePower\u003c\/span\u003e\u003cbr\u003e\u003cspan style=\"font-size: 18px;\"\u003eConsumption\u003c\/span\u003e\n\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eNormal: 1.2W(12V\/100mA)，Max: 6W(12V\/500mA)，Min: 0.096W(12V\/8mA)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eSize\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e93.00mm * 60.15mm * 12.49mm\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eWeight\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e≈50g\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eEnvironment\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eOperating temperature: -20℃- 60℃\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eStorage humidity: 10%～90%RH (non-condensing)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"7\" class=\"new_param_left_title\" style=\"width: 13.875%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eInterfaces\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eNetwork\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * Gigabit Ethernet (1000 Mbps \/ RJ45), 2.4GHz\/5GHz dual-band WiFi (802.11a\/b\/g\/n\/ac), Bluetooth 5.0\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eVideo Input\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * MIPI CSI DPHY (30Pin-0.5mm, 1*4 lanes\/2*2 lanes)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eVideo Output\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * HDMI2.1(4K@120fps)、1 * DP1.4 (4K@120fps)、\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * MIPI DSI DPHY（2560*1600@60fps，30Pin-0.5mm, 1*4 lanes）\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eWatchdog\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003eExternal watchdog\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\u003cspan style=\"font-size: 18px;\"\u003eUSB\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * USB3.0、1 * USB2.0\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"new_param_left\" style=\"width: 9.375%;\"\u003e\n\u003cspan style=\"font-size: 18px;\"\u003eExpansion\u003c\/span\u003e\u003cbr\u003e\u003cspan style=\"font-size: 18px;\"\u003eInterface\u003c\/span\u003e\n\u003c\/td\u003e\n\u003ctd class=\"new_param_right\" style=\"width: 76.75%;\"\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * Type-C (OTG\/DP1.4), 1 * FAN (4Pin-1.25mm), 1 * Debug (3Pin-2mm),\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * 3.5mm Audio jack (supporting MIC recording, CTIA standard), 1 * MIC (2Pin-1.25mm)\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 18px;\"\u003e1 * double-row pin header (20Pin-2.0mm): USB 2.0, I2C, SPI, SARADC, UART, and LineOut\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003ch2\u003e\n\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e\u003cbr\u003eDetailed Descriptions\u003c\/span\u003e\u003c\/b\u003e\u003cb\u003e\u003cspan data-font-family=\"default\"\u003e \u003c\/span\u003e\u003c\/b\u003e\n\u003c\/h2\u003e\n\u003chr\u003e\n\u003cp\u003e\u003cspan data-font-family=\"default\" style=\"font-size: 18px;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10001.jpg?v=1792314690\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10002.jpg?v=1792314691\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10003.jpg?v=1792314691\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10004.jpg?v=1792314690\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10005.jpg?v=1792314690\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10006.jpg?v=1792314691\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10007.jpg?v=1792314691\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/roc-rk3576-pc-10008.jpg?v=1792314691\"\u003e\u003c\/span\u003e\u003c\/p\u003e","brand":"youyeetoo","offers":[{"title":"4GB RAM 32GB ROM","offer_id":42393334644834,"sku":"TQTC357601","price":1279.0,"currency_code":"HKD","in_stock":true},{"title":"8GB RAM 64GB ROM","offer_id":42393334677602,"sku":"TQTC357602","price":1521.0,"currency_code":"HKD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0652\/9443\/4402\/files\/7b393ac959.jpg?v=1793927941","url":"https:\/\/youyeetoo.com\/products\/roc-rk3576-pc-low-power-large-model-mini-computer","provider":"youyeetoo","version":"1.0","type":"link"}