{"content_id":"d0l5vvwtfy","slug":"nvidia-rubin-hpc-announced-availability-expected-2028","locale":"en","schema_type":"NewsArticle","category":"news","category_name":"News","title":"NVIDIA Rubin HPC Announced, Expected to Ship in 2028","summary":"NVIDIA announced Rubin HPC, a GPU for science and engineering, and said it expects availability in 2028. A single GPU has more than 50,000 CUDA cores, while availability in South Korea and pricing have not been disclosed.","sponsorship_disclosure":null,"affiliate_disclosure":null,"commerce_disclosure":null,"author":{"name":"Injoys Editorial Team","url":"https://injoys.com/ko/about"},"key_points":["NVIDIA said it expects Rubin HPC to be available in 2028.","According to NVIDIA's announcement, a single Rubin HPC GPU has more than 50,000 CUDA cores.","Rubin HPC uses 7th-generation NVIDIA NVLink for connections between GPUs.","Availability in South Korea, local purchasing channels, pricing, and when orders will open have not been disclosed.","The announcement does not include memory specifications, power consumption, FP64 compute performance, or independent performance test results."],"content_markdown":"NVIDIA announced Rubin HPC for science and engineering on November 16, 2026. In Korean time, this was 1 a.m. on November 17. It is expected to be available in **2028**. NVIDIA did not disclose whether orders can currently be placed.\n\nThis article is based on NVIDIA's announcement and was checked as of November 17, 2026.\n\n## Rubin HPC announced for scientific and engineering computing\n\nNVIDIA announced Rubin HPC, a GPU for scientific and engineering computing. It uses 7th-generation NVIDIA NVLink for connections between GPUs. This announcement provides an expected availability date and does not mark the start of sales.\n\n## Availability expected in 2028, with no schedule disclosed for Korea\n\nNVIDIA said it expects Rubin HPC to be available in 2028. This is the company's estimated schedule. It did not disclose a specific availability date within 2028.\n\nThe announcement also does not confirm whether it will be available in Korea. Purchasing channels in Korea have not been disclosed either. It is therefore not yet possible to specify when research institutions or companies in Korea will be able to use it.\n\n## Pricing and ordering dates not disclosed\n\nThe announcement does not include pricing for Rubin HPC. It also does not disclose when orders can be placed. The expected year of availability alone does not establish that orders or contracts can be placed.\n\n## CUDA core and interconnect specifications as announced by NVIDIA\n\nThe specifications NVIDIA announced on November 16, 2026, are as follows. The figures in the table are product specifications provided by the company. They are not computing performance figures measured by an independent organization.\n\n| Item | NVIDIA's announcement | What the figure represents |\n| --- | --- | --- |\n| CUDA core count | More than 50,000 | Number of cores on a single GPU |\n| Connections between GPUs | 7th-generation NVIDIA NVLink | Generation of GPU interconnect technology |\n\nThe CUDA core count is **more than 50,000 per GPU**. This does not mean exactly 50,000. FP64 computing performance cannot be calculated from this core count alone.\n\n## Memory, power consumption, and FP64 performance not confirmed\n\nThe announcement does not include detailed memory or power specifications. FP64 computing performance was not provided either. No independent performance measurement results have been confirmed.\n\n| Undisclosed item | Further information to confirm |\n| --- | --- |\n| Memory | Type, capacity, bandwidth |\n| Power | Power consumption |\n| Computing performance | FP64 computing performance |\n| Independent verification | Performance measurement results obtained independently of the company's announcement |\n\n## Items to check before considering adoption in Korea\n\nAnyone considering adoption in Korea must first confirm whether the product will be available there. Comparing prices or performance also requires specifications that have not been disclosed. The following items should be checked in NVIDIA's subsequent announcements and product documentation.\n\n- Availability in Korea and purchasing channels in Korea\n- Specific availability schedule and when orders can be placed\n- Pricing and memory type, capacity, and bandwidth\n- Power consumption and FP64 computing performance\n\nIndependent performance measurement results should be checked separately from the company's specification announcements. The current announcement alone does not establish the extent of any performance improvement over existing equipment. When the product will be available for purchase in Korea also requires further confirmation.","content_html":"\u003cp\u003eNVIDIA announced Rubin HPC for science and engineering on November 16, 2026. In Korean time, this was 1 a.m. on November 17. It is expected to be available in \u003cstrong\u003e2028\u003c/strong\u003e. NVIDIA did not disclose whether orders can currently be placed.\u003c/p\u003e\n\u003cp\u003eThis article is based on NVIDIA's announcement and was checked as of November 17, 2026.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#rubin-hpc-announced-for-scientific-and-engineering-computing\" class=\"anchor\" id=\"rubin-hpc-announced-for-scientific-and-engineering-computing\"\u003e\u003c/a\u003eRubin HPC announced for scientific and engineering computing\u003c/h2\u003e\n\u003cp\u003eNVIDIA announced Rubin HPC, a GPU for scientific and engineering computing. It uses 7th-generation NVIDIA NVLink for connections between GPUs. This announcement provides an expected availability date and does not mark the start of sales.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#availability-expected-in-2028-with-no-schedule-disclosed-for-korea\" class=\"anchor\" id=\"availability-expected-in-2028-with-no-schedule-disclosed-for-korea\"\u003e\u003c/a\u003eAvailability expected in 2028, with no schedule disclosed for Korea\u003c/h2\u003e\n\u003cp\u003eNVIDIA said it expects Rubin HPC to be available in 2028. This is the company's estimated schedule. It did not disclose a specific availability date within 2028.\u003c/p\u003e\n\u003cp\u003eThe announcement also does not confirm whether it will be available in Korea. Purchasing channels in Korea have not been disclosed either. It is therefore not yet possible to specify when research institutions or companies in Korea will be able to use it.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#pricing-and-ordering-dates-not-disclosed\" class=\"anchor\" id=\"pricing-and-ordering-dates-not-disclosed\"\u003e\u003c/a\u003ePricing and ordering dates not disclosed\u003c/h2\u003e\n\u003cp\u003eThe announcement does not include pricing for Rubin HPC. It also does not disclose when orders can be placed. The expected year of availability alone does not establish that orders or contracts can be placed.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#cuda-core-and-interconnect-specifications-as-announced-by-nvidia\" class=\"anchor\" id=\"cuda-core-and-interconnect-specifications-as-announced-by-nvidia\"\u003e\u003c/a\u003eCUDA core and interconnect specifications as announced by NVIDIA\u003c/h2\u003e\n\u003cp\u003eThe specifications NVIDIA announced on November 16, 2026, are as follows. The figures in the table are product specifications provided by the company. They are not computing performance figures measured by an independent organization.\u003c/p\u003e\n\u003cdiv class=\"overflow-x-auto\"\u003e\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003eItem\u003c/th\u003e\n\u003cth\u003eNVIDIA's announcement\u003c/th\u003e\n\u003cth\u003eWhat the figure represents\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Item\"\u003eCUDA core count\u003c/td\u003e\n\u003ctd data-label=\"NVIDIA's announcement\"\u003eMore than 50,000\u003c/td\u003e\n\u003ctd data-label=\"What the figure represents\"\u003eNumber of cores on a single GPU\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Item\"\u003eConnections between GPUs\u003c/td\u003e\n\u003ctd data-label=\"NVIDIA's announcement\"\u003e7th-generation NVIDIA NVLink\u003c/td\u003e\n\u003ctd data-label=\"What the figure represents\"\u003eGeneration of GPU interconnect technology\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\u003c/div\u003e\n\u003cp\u003eThe CUDA core count is \u003cstrong\u003emore than 50,000 per GPU\u003c/strong\u003e. This does not mean exactly 50,000. FP64 computing performance cannot be calculated from this core count alone.\u003c/p\u003e\n\u003ch2\u003e\n\u003ca href=\"#memory-power-consumption-and-fp64-performance-not-confirmed\" class=\"anchor\" id=\"memory-power-consumption-and-fp64-performance-not-confirmed\"\u003e\u003c/a\u003eMemory, power consumption, and FP64 performance not confirmed\u003c/h2\u003e\n\u003cp\u003eThe announcement does not include detailed memory or power specifications. FP64 computing performance was not provided either. No independent performance measurement results have been confirmed.\u003c/p\u003e\n\u003cdiv class=\"overflow-x-auto\"\u003e\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003eUndisclosed item\u003c/th\u003e\n\u003cth\u003eFurther information to confirm\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Undisclosed item\"\u003eMemory\u003c/td\u003e\n\u003ctd data-label=\"Further information to confirm\"\u003eType, capacity, bandwidth\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Undisclosed item\"\u003ePower\u003c/td\u003e\n\u003ctd data-label=\"Further information to confirm\"\u003ePower consumption\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Undisclosed item\"\u003eComputing performance\u003c/td\u003e\n\u003ctd data-label=\"Further information to confirm\"\u003eFP64 computing performance\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd data-label=\"Undisclosed item\"\u003eIndependent verification\u003c/td\u003e\n\u003ctd data-label=\"Further information to confirm\"\u003ePerformance measurement results obtained independently of the company's announcement\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\u003c/div\u003e\n\u003ch2\u003e\n\u003ca href=\"#items-to-check-before-considering-adoption-in-korea\" class=\"anchor\" id=\"items-to-check-before-considering-adoption-in-korea\"\u003e\u003c/a\u003eItems to check before considering adoption in Korea\u003c/h2\u003e\n\u003cp\u003eAnyone considering adoption in Korea must first confirm whether the product will be available there. Comparing prices or performance also requires specifications that have not been disclosed. The following items should be checked in NVIDIA's subsequent announcements and product documentation.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eAvailability in Korea and purchasing channels in Korea\u003c/li\u003e\n\u003cli\u003eSpecific availability schedule and when orders can be placed\u003c/li\u003e\n\u003cli\u003ePricing and memory type, capacity, and bandwidth\u003c/li\u003e\n\u003cli\u003ePower consumption and FP64 computing performance\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eIndependent performance measurement results should be checked separately from the company's specification announcements. The current announcement alone does not establish the extent of any performance improvement over existing equipment. When the product will be available for purchase in Korea also requires further confirmation.\u003c/p\u003e\n","tags":["Semiconductors","AI chips","Technology strategy"],"faqs":[{"question":"Can Rubin HPC be ordered in Korea now?","answer":"The announcement did not disclose whether Rubin HPC would be supplied in Korea or the purchasing channels in Korea. It also did not say when orders would open, so it is not possible to confirm whether it can currently be ordered in Korea."},{"question":"Will Rubin HPC also be available for use in Korea by 2028?","answer":"NVIDIA said it expects to supply it in 2028, but it did not provide a supply schedule for Korea. It also did not disclose exactly when in 2028 it would be supplied."},{"question":"Can the cost of adopting it in Korea and its scientific computing performance be assessed?","answer":"The announcement does not include pricing or power consumption. FP64 computing performance and independent performance test results have not been disclosed either. The announced CUDA core count alone is not enough to assess the cost of adopting it or its actual computing performance."}],"sources":[{"url":"https://blogs.nvidia.com/blog/rubin-hpc/","title":"NVIDIA Announces Rubin HPC: A New GPU to Accelerate Agents for Science, Engineering and Analytics - NVIDIA","type":"source"}],"images":[{"id":3022,"url":"https://injoys.com/rails/active_storage/blobs/proxy/eyJfcmFpbHMiOnsiZGF0YSI6NDU3MjQsInB1ciI6ImJsb2JfaWQifX0=--75774cbe26e0becd470804e0a01065676c63199d/ai-7c9492ce.webp","is_representative":true,"generation_method":"ai_photo","license":"ai_generated","mime_type":"image/webp","width":1536,"height":1024,"translations":{"ko":{"alt":"실험실 작업대의 검은 보호 받침에 놓인 대형 금속 프로세서와 구리 방열판을 갖춘 무상표 GPU 보드","caption":"NVIDIA는 과학·공학 연산용 Rubin HPC를 2028년에 공급할 것으로 예상한다.","description":null},"en":{"alt":"Unbranded GPU board with a large metal processor and copper heatsinks in a protective cradle on a lab bench","caption":"NVIDIA expects Rubin HPC for scientific and engineering computing to be available in 2028.","description":null},"ja":{"alt":"研究室の作業台で黒い保護台に置かれた、大型の金属製プロセッサと銅製ヒートシンクを備える無銘のGPU基板","caption":"NVIDIAは、科学・工学計算向けのRubin HPCを2028年に供給する見通しを示した。","description":null},"es":{"alt":"Placa GPU sin marca con un gran procesador metálico y disipadores de cobre sobre un soporte protector de laboratorio","caption":"NVIDIA prevé que Rubin HPC para computación científica y de ingeniería esté disponible en 2028.","description":null},"id":{"alt":"Papan GPU tanpa merek dengan prosesor logam besar dan heatsink tembaga di dudukan pelindung pada meja laboratorium","caption":"NVIDIA memperkirakan Rubin HPC untuk komputasi sains dan teknik akan tersedia pada 2028.","description":null},"pt":{"alt":"Placa de GPU sem marca com grande processador metálico e dissipadores de cobre em suporte protetor na bancada","caption":"A NVIDIA prevê que o Rubin HPC para computação científica e de engenharia esteja disponível em 2028.","description":null},"zh-hant":{"alt":"實驗室工作檯上的無品牌GPU電路板，置於黑色保護托架內，配有大型金屬處理器及銅製散熱片","caption":"NVIDIA預計於2028年供應用於科學與工程運算的Rubin HPC。","description":null},"de":{"alt":"Markenlose GPU-Platine mit großem Metallprozessor und Kupferkühlkörpern in einer Schutzhalterung auf dem Labortisch","caption":"NVIDIA erwartet, Rubin HPC für wissenschaftliche und technische Berechnungen 2028 liefern zu können.","description":null}}},{"id":3023,"url":"https://injoys.com/rails/active_storage/blobs/proxy/eyJfcmFpbHMiOnsiZGF0YSI6NDU3MzAsInB1ciI6ImJsb2JfaWQifX0=--bcf8bed7bbb470afda05d60f0957e17b13238419/ai-f08a1e1c.webp","is_representative":false,"generation_method":"ai_semi","license":"ai_generated","mime_type":"image/webp","width":1536,"height":1024,"translations":{"ko":{"alt":"서버실에서 여성이 열린 서버 랙의 케이블을 가리키고 옆의 남성이 살펴보고 있다.","caption":"Rubin HPC는 GPU 간 연결에 7세대 NVIDIA NVLink를 적용한다.","description":null},"en":{"alt":"A woman gestures toward cables in an open server rack while a man looks on.","caption":"Rubin HPC will use seventh-generation NVIDIA NVLink for GPU-to-GPU connectivity.","description":null},"ja":{"alt":"サーバー室で女性が開いたサーバーラックのケーブルを指し示し、隣の男性が見ている。","caption":"Rubin HPCはGPU間の接続に第7世代NVIDIA NVLinkを採用する。","description":null},"es":{"alt":"Una mujer señala los cables de un rack de servidores abierto mientras un hombre observa.","caption":"Rubin HPC utilizará NVIDIA NVLink de séptima generación para la conexión entre GPU.","description":null},"id":{"alt":"Seorang perempuan menunjuk kabel di rak server terbuka sementara seorang laki-laki memperhatikan.","caption":"Rubin HPC akan menggunakan NVIDIA NVLink generasi ketujuh untuk koneksi antar-GPU.","description":null},"pt":{"alt":"Uma mulher aponta para os cabos de um rack de servidores aberto enquanto um homem observa.","caption":"O Rubin HPC usará NVIDIA NVLink de sétima geração para a conexão entre GPUs.","description":null},"zh-hant":{"alt":"一名女性指向開啟的伺服器機櫃內的纜線，旁邊一名男性正在查看。","caption":"Rubin HPC 將採用第七代 NVIDIA NVLink 進行 GPU 之間的連接。","description":null},"de":{"alt":"Eine Frau deutet auf Kabel in einem offenen Serverrack, während ein Mann zusieht.","caption":"Rubin HPC wird NVIDIA NVLink der siebten Generation für die Verbindung zwischen GPUs nutzen.","description":null}}}],"published_at":"2026-11-17T17:01:29+09:00","updated_at":"2026-11-17T17:01:29+09:00","license":"cc_by","translation_status":"reviewed","available_locales":["ko","en","ja","es"],"data_locales":["ko","en","ja","es","id","pt","zh-hant","de"],"url":"https://injoys.com/en/articles/nvidia-rubin-hpc-announced-availability-expected-2028"}