{"product_id":"nvidia-900-13834-0080-000-jetson-thor-t5000-ai-module-2070-tflops-128gb","title":"NVIDIA 900-13834-0080-000 | Jetson Thor T5000 AI Module, 2070 TFLOPS, 128GB","description":"\u003cp\u003eThe Jetson Thor T5000 is a production system-on-module from the NVIDIA Jetson Thor series, built for humanoid robotics and physical AI. It is aimed at developers and OEMs building autonomous machines, agentic AI at the edge, and systems that run generative AI models such as VLAs, LLMs and VLMs locally.\u003c\/p\u003e\u003cp\u003eAt its core is a 2560-core Blackwell GPU with 96 fifth-generation Tensor Cores, delivering up to 2070 FP4 TFLOPS (sparse). It is paired with a 14-core Arm Neoverse-V3AE CPU running up to 2.6 GHz and 128 GB of 256-bit LPDDR5X memory with 273 GB\/s of bandwidth. Networking is handled by 4x 25 GbE, and the module supports up to 20 cameras via the Holoscan Sensor Bridge. Module power is configurable between 40 W and 130 W. NVIDIA positions it at over 7.5x the AI compute of Jetson AGX Orin with 3.5x better energy efficiency.\u003c\/p\u003e\u003cp\u003eThe module uses a 699-pin board-to-board connector and an integrated thermal transfer plate with heatpipe, and measures 100 mm x 87 mm. It requires a Jetson Thor-compatible carrier board, with the Jetson AGX Thor Developer Kit as the reference platform, plus a matching thermal solution. It is supported by the NVIDIA Jetson Linux and JetPack software stack, the Isaac platform and GR00T foundation models.\u003c\/p\u003e\u003cp\u003eEnquire with XS Network Tech for new or used pricing and availability.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":67729101619370,"sku":"900-13834-0080-000","price":0.0,"currency_code":"AUD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0661\/9181\/8922\/files\/Jetson_T5000_Module-700x700_1.png?v=1792715228","url":"https:\/\/www.xsnet.com.au\/products\/nvidia-900-13834-0080-000-jetson-thor-t5000-ai-module-2070-tflops-128gb","provider":"XS Network Tech","version":"1.0","type":"link"}