{"id":222374,"date":"2024-04-10T11:24:50","date_gmt":"2024-04-10T11:24:50","guid":{"rendered":"https:\/\/michigandigitalnews.com\/index.php\/2024\/04\/10\/intel-unveils-gaudi-3-ai-accelerator-says-it-beats-nvidias-h100\/"},"modified":"2025-06-25T17:18:54","modified_gmt":"2025-06-25T17:18:54","slug":"intel-unveils-gaudi-3-ai-accelerator-says-it-beats-nvidias-h100","status":"publish","type":"post","link":"https:\/\/michigandigitalnews.com\/index.php\/2024\/04\/10\/intel-unveils-gaudi-3-ai-accelerator-says-it-beats-nvidias-h100\/","title":{"rendered":"Intel unveils Gaudi 3 AI accelerator, says it beats Nvidia’s H100"},"content":{"rendered":"

[ad_1]
\n<\/p>\n

\n

Intel kicked off its Vision 2024 conference with the unveiling of the Gaudi 3 AI processing chip. Gaudi 3 is designed to accelerate AI workloads at an enterprise level, and Intel reckons it’s faster than the current industry benchmark – Nvidia’s H100 GPU.<\/p>\n

Gaudi 3 uses the same architecture and underlying principles as Gaudi 2, but it uses TSMC’s 5nm process (compared to TSMC’s 7nm in Gaudi 2), making it more efficient.<\/p>\n

Gaudi 3 has up to 128GB of HBM2e with 3.7 TB\/s of bandwidth and 900W TDP.<\/p>\n

\"Intel<\/p>\n

Intel showed benchmarks comparing Gaudi 3 to market leader Nvidia and its dominating H100 GPU, running different large language models like LLAMA2-7B, LLAMA2-13B, and GPT 3-175B. Gaudi 3 is up to 1.7x faster.<\/p>\n

Intel also says that Gaudi 3 is up to 2.3 times more power efficient than Nvidia’s H100.<\/p>\n

\"Intel<\/p>\n

Intel has already sent air-cooled Gaudi 3 models for sampling to partners with general availability to follow in Q3. Liquid-cooled units will come in Q4.<\/p>\n

Source<\/a><\/p>\n<\/div>\n

[ad_2]
\n
Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

[ad_1] Intel kicked off its Vision 2024 conference with the unveiling of the Gaudi 3 AI processing chip. Gaudi 3 is designed to accelerate AI<\/p>\n","protected":false},"author":1,"featured_media":222375,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_uf_show_specific_survey":0,"_uf_disable_surveys":false,"footnotes":""},"categories":[165],"tags":[],"_links":{"self":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/posts\/222374"}],"collection":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/comments?post=222374"}],"version-history":[{"count":0,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/posts\/222374\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/media\/222375"}],"wp:attachment":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/media?parent=222374"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/categories?post=222374"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/tags?post=222374"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}