--- format: "aidr-story-markdown/v1" id: "591815dc92bc137c469f3cdf0f8d87af0e52f7f17654113d19a0f9d8ce72a38e" canonical_url: "https://aidr.today/591815dc?lang=en" title: "SpaceXAI Deploys Nvidia Vera Rubin on Starmind Satellite in First Orbital AI Factory" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-08-24T16:52:09.000Z" category: "Infra" topics: ["nvidia","grok","agent","inference","chips","spacex","infra"] source_urls: ["https://huggingnews.com/ai/spacexai-deploys-nvidia-vera-rubin-on-starmind-satellite-in-first-orbita-8144234c","https://x.com/nvidia/status/2091920680317046847","https://x.com/SawyerMerritt/status/2091911938947035434","https://x.com/wallstengine/status/2091904569320312908","https://x.com/FirstSquawk/status/2091903731373891633","https://x.com/wallstengine/status/2091903365030506957","https://x.com/nvidianewsroom/status/2091910170796298448","https://x.com/elonmusk/status/2091939113008238838"] summary: "The Grok AI model is scaling toward gigawatt compute capacity using a new processor architecture designed to handle complex tool orchestration and code execution. SpaceXAI is deploying Nvidia Vera CPUs for these agentic AI workloads and utilizing the Vera Rubin NVL72 rack-scale system for its first-generation Starmind AI satellite. This partnership establishes a uniform computing foundation from terrestrial data centers to orbital infrastructure, standardizing the software ecosystem across both environments. The Vera CPU features 88 Olympus cores and up to 1.2 TB/s of memory bandwidth, which Nvidia says provides 1.8x faster task completion than x86 CPUs for certain agentic tasks. The processor is intended to offload CPU-heavy inference work to ensure that GPUs remain focused on model workloads. To enable orbital deployment, the companies are adapting the system to withstand the specific thermal, power, and reliability constraints of space." --- # SpaceXAI Deploys Nvidia Vera Rubin on Starmind Satellite in First Orbital AI Factory > [Open the canonical story]() **Published:** 2026-08-24T16:52:09.000Z **Category:** Infra **Topics:** nvidia, grok, agent, inference, chips, spacex, infra ## Summary The Grok AI model is scaling toward gigawatt compute capacity using a new processor architecture designed to handle complex tool orchestration and code execution\. SpaceXAI is deploying Nvidia Vera CPUs for these agentic AI workloads and utilizing the Vera Rubin NVL72 rack\-scale system for its first\-generation Starmind AI satellite\. This partnership establishes a uniform computing foundation from terrestrial data centers to orbital infrastructure, standardizing the software ecosystem across both environments\. The Vera CPU features 88 Olympus cores and up to 1\.2 TB/s of memory bandwidth, which Nvidia says provides 1\.8x faster task completion than x86 CPUs for certain agentic tasks\. The processor is intended to offload CPU\-heavy inference work to ensure that GPUs remain focused on model workloads\. To enable orbital deployment, the companies are adapting the system to withstand the specific thermal, power, and reliability constraints of space\. ## Sources - [Story source]() - [Story source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Story source]() - [Story source]()