{"id":16320,"date":"2025-05-08T13:56:11","date_gmt":"2025-05-08T11:56:11","guid":{"rendered":"https:\/\/quantum.com.pl\/product\/inference-server-powered-by-nvidia-jetson-orin-nx\/"},"modified":"2025-05-19T15:25:08","modified_gmt":"2025-05-19T13:25:08","slug":"inference-server-powered-by-nvidia-jetson-orin-nx","status":"publish","type":"product","link":"https:\/\/quantum.com.pl\/en\/product\/inference-server-powered-by-nvidia-jetson-orin-nx\/","title":{"rendered":"Inference Server, Powered by NVIDIA Jetson Orin NX"},"content":{"rendered":"

Specifications:<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n
<\/th>\n\u2022 24x NVIDIA\u00ae Jetson Orin™ NX
\n\u2022 GPU: 1024-core CUDA GPU with 32 Tensor Cores, 3.7 TFLOPS (FP16), 100 TOPs (INT8)
\n\u2022 CPU: 8-core Cortex Arm v8.2 CPU, 2MB L2 + 4MB L3
\n\u2022 Memory: 16 GB 128-bit LPDDR5, 102.4GB\/s
\n\u2022 Storage: Supports External Storage (NVMe) via x4 PCIe<\/td>\n<\/tr>\n
Out-of-band Management Module<\/th>\n\u2022 ARM based OOBM
\n\u2022 Enabling Serial console access, power status monitoring, and power control (ON\/OFF) to all 24x Orin NX modules
\n\u2022 OOBM accessible via Ethernet or via its own integrated USB-to-Serial console<\/td>\n<\/tr>\n
Processor Module Carriers<\/th>\n\u2022 Each module carrier will allow up to 8x Orin NX modules to be installed
\n\u2022 3x module carriers can be installed in the system for a total of 24 modules<\/td>\n<\/tr>\n
Internal Embedded Ethernet Switch<\/th>\n\u2022 Vitesse\/Microsemi SparX-5i VSC7558TSN-V\/5CC Managed Ethernet Switch Engine (XDG205)
\n\u2022 CPU: 1 GHz VCore
\n\u2022 Memory: 8Gb DDR4 SDRAM
\n\u2022 Storage: 1Gbit Serial NOR Flash
\n\u2022 Multi 10G uplinks, with 12x 1G downstream
\n\u2022 Complete TSN feature set (Time-Sensitive Networking)<\/td>\n<\/tr>\n
Internal Array Communication<\/th>\n\u2022 24x Gigabit Ethernet \/ 1000BASE-T \/ IEEE 802.3ab channels
\n\u2022 All Orin NX modules can communicate to all other Orin NX modules<\/td>\n<\/tr>\n
External Uplink Connections<\/th>\n\u2022 4x SFP+ 10G uplink<\/td>\n<\/tr>\n
Misc \/ Additional IO<\/th>\n1x 1GbE OOB management port via RJ-45; 1x USB UART management port; status LEDs<\/td>\n<\/tr>\n
Input Power<\/th>\n100~240 VAC (dual redundant) with 1000W output each<\/td>\n<\/tr>\n
Internal Storage<\/th>\nEach Orin NX module has its own M.2 NVMe interface<\/td>\n<\/tr>\n
Operating Temperature<\/th>\n0\u00b0C to +50\u00b0C (+32\u00b0F to +122\u00b0F)<\/td>\n<\/tr>\n
Dimensions<\/th>\nStandard 2U rackmount height (3.5 inch \/ 88.9mm), 25 inch \/ 635mm depth<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Ordering Information<\/h3>\n

UNGX2U-07<\/strong> \u00a0\u00a0\u00a0 Orin NX Inference Server \u2013 2U Array, with 24x NVIDIA Jetson Orin NX 16GB, 24x 1TB NVMe SSD
\nUNGX2U-08<\/strong> \u00a0\u00a0 Orin NX Inference Server \u2013 2U Array, with 16x NVIDIA Jetson Orin NX 16GB, 16x 1TB NVMe SSD
\nUNGX2U-09<\/strong> \u00a0\u00a0 Orin NX Inference Server \u2013 2U Array, with 8x NVIDIA Jetson Orin NX 16GB, 8x 1TB NVMe SSD
\nUNGX2U-10\u00a0\u00a0<\/strong> \u00a0 Orin NX Inference Server \u2013 2U Array, with 24x NVIDIA Jetson Orin NX 16GB, 24x 2TB NVMe SSD
\nUNGX2U-11<\/strong> \u00a0\u00a0\u00a0\u00a0 Orin NX Inference Server \u2013 2U Array, with 16x NVIDIA Jetson Orin NX 16GB, 16x 2TB NVMe SSD
\nUNGX2U-12<\/strong> \u00a0\u00a0\u00a0\u00a0 Orin NX Inference Server \u2013 2U Array, with 8x NVIDIA Jetson Orin NX 16GB, 8x 2TB NVMe SSD<\/p>\n","protected":false},"excerpt":{"rendered":"

Highlights:<\/h3>\n
    \n
  • 24x 100 TOPS, 1024-core NVIDIA GPU and 32 Tensor Cores<\/li>\n
  • 4x 10G SFP+ uplink capability<\/li>\n
  • Supports External NVMe Storage<\/li>\n
  • 2U ATX style redundant power supply<\/li>\n
  • Operating Temperature: 0\u00b0C to +50\u00b0C (+32\u00b0F to +122\u00b0F)<\/li>\n<\/ul>\n

    More information:<\/strong><\/p>\n

    Housed in a 2U chassis, the Orin NX Inference Server can be outfitted with up to 24x NVIDIA Jetson Orin NX modules.<\/p>\n

    Developed in partnership with USES Integrated Solutions, the Orin NX Inference Server is an extremely low wattage, high performance deep learning inference server powered by the NVIDIA Jetson Orin NX 16GB module. Within the Server, three processor module carriers house up to eight Jetson Orin NX modules each, and are all connected via a Gigabit Ethernet fabric through a specialized Managed Ethernet Switch developed by Connect Tech with 10G uplink capability (XDG205).<\/p>\n","protected":false},"featured_media":16318,"template":"","meta":{"_acf_changed":false,"inline_featured_image":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0},"product_brand":[],"product_cat":[1489,1690],"product_tag":[],"class_list":{"0":"post-16320","1":"product","2":"type-product","3":"status-publish","4":"has-post-thumbnail","6":"product_cat-connect-tech-inc-en","7":"product_cat-nvidia-jetson-orin-nx-en","9":"first","10":"instock","11":"shipping-taxable","12":"product-type-simple"},"acf":[],"_links":{"self":[{"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/product\/16320","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/product"}],"about":[{"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/types\/product"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/media\/16318"}],"wp:attachment":[{"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/media?parent=16320"}],"wp:term":[{"taxonomy":"product_brand","embeddable":true,"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/product_brand?post=16320"},{"taxonomy":"product_cat","embeddable":true,"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/product_cat?post=16320"},{"taxonomy":"product_tag","embeddable":true,"href":"https:\/\/quantum.com.pl\/en\/wp-json\/wp\/v2\/product_tag?post=16320"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}