{"id":122456,"date":"2025-03-18T08:22:21","date_gmt":"2025-03-18T06:22:21","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/amd-pohvastalas-chto-ryzen-ai-max-395-do-12-raz-bystree-v-rabote-s-ii-chem-pryamoj-konkurent-ot-intel"},"modified":"2025-03-18T08:22:21","modified_gmt":"2025-03-18T06:22:21","slug":"amd-pohvastalas-chto-ryzen-ai-max-395-do-12-raz-bystree-v-rabote-s-ii-chem-pryamoj-konkurent-ot-intel","status":"publish","type":"post","link":"https:\/\/prohoster.info\/nl\/blog\/news\/amd-pohvastalas-chto-ryzen-ai-max-395-do-12-raz-bystree-v-rabote-s-ii-chem-pryamoj-konkurent-ot-intel","title":{"rendered":"AMD heeft gepromoot dat de Ryzen AI Max+ 395 tot 12 keer sneller is in het werken met AI dan de directe concurrent van Intel.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>De nieuwste vlaggenschip mobiel processor AMD Ryzen AI Max+ 395 van de Strix Halo-serie biedt tot 12 keer hogere prestaties bij het werken met verschillende grote AI-taalmodellen dan de Intel Lunar Lake-chips. Dit heeft AMD <noindex><a rel=\"nofollow\" href=\"https:\/\/community.amd.com\/t5\/ai\/amd-ryzen-ai-max-395-processor-breakthrough-ai-performance-in\/ba-p\/752960\" target=\"_blank\">meldde<\/a><\/noindex> gedeeld op zijn offici\u00eble blog, vergezeld van relevante diagrammen.<\/p>\n<p><center><\/center> \t\t\t\t<center><\/center>  <img decoding=\"async\" alt=\"AMD heeft gepromoot dat de Ryzen AI Max+ 395 tot 12 keer sneller is in het werken met AI dan de directe concurrent van Intel.\" src=\"\/wp-content\/uploads\/2025\/03\/cae43eacff102641101b251a1f5f6a63.jpg\" style=\"display:block;margin: 0 auto;\" \/>    <\/p>\n<p>Dankzij 16 Zen 5-rekenkernen, 40 RDNA 3.5 grafische eenheden en een NPU XDNA 2 met een prestatie van 50 TOPS (triljard operaties per seconde), biedt de Ryzen AI Max+ 395 tot 12,2 keer hogere prestaties in bepaalde LLM-scenario's dan de Intel Core Ultra 258V. Ter herinnering, de Intel Lunar Lake-chip bevat slechts vier P-kernen en vier E-kernen, wat in totaal de helft is van de Ryzen AI Max+ 395. Echter, het prestatieverschil tussen de platforms is veel groter dan twee keer.<\/p>\n<p> <img decoding=\"async\" alt=\"AMD heeft gepromoot dat de Ryzen AI Max+ 395 tot 12 keer sneller is in het werken met AI dan de directe concurrent van Intel.\" src=\"\/wp-content\/uploads\/2025\/03\/dbde45e5bbd47cf2159d50cfebb11360.jpg\" style=\"display:block;margin: 0 auto;\" \/> <\/p>\n<p>Het voordeel van de Ryzen AI Max+ 395-chip wordt nog duidelijker naarmate de complexiteit van de taalmodellen toeneemt. Het grootste prestatieverschil tussen de platforms is zichtbaar bij het werken met LLM's met 14 miljard parameters, waar meer werkgeheugen nodig is. Lunar Lake zijn hybride processors die tot 32 GB aan boordgeheugen hebben. <\/p>\n<p><center><\/center> <img decoding=\"async\" alt=\"AMD heeft gepromoot dat de Ryzen AI Max+ 395 tot 12 keer sneller is in het werken met AI dan de directe concurrent van Intel.\" src=\"\/wp-content\/uploads\/2025\/03\/4ca31e62e719ac5ed0fd2185d39ad799.jpg\" style=\"display:block;margin: 0 auto;\" \/> <\/p>\n<p>In de tests van LM Studio, uitgevoerd met het apparaat Asus ROG Flow Z13 met 64 GB unifi\u00e9e geheugen, toonde de ge\u00efntegreerde Radeon 8060S grafische chip van de Ryzen AI Max+ 395 een 2,2 keer grotere token-doorvoer dan de Intel Arc 140V in verschillende AI-modellen. In de Time-to-First-Token-tests (een prestatiemetriek voor taalmodellen die laat zien hoe lang het duurt vanaf het verzenden van een aanvraag tot de generatie van de eerste respons-token) liet de AMD-chip een vier keer groter voordeel zien ten opzichte van de concurrent in modellen zoals Llama 3.2 3B Instruct, en vergrootte het verschil tot 9,1 keer in modellen die 7\u20138 miljard parameters ondersteunen, zoals DeepSeek R1 Distill.<\/p>\n<p> <img decoding=\"async\" alt=\"AMD heeft gepromoot dat de Ryzen AI Max+ 395 tot 12 keer sneller is in het werken met AI dan de directe concurrent van Intel.\" src=\"\/wp-content\/uploads\/2025\/03\/54653fc92e8620551d4703037e07e8fd.jpg\" style=\"display:block;margin: 0 auto;\" \/> <\/p>\n<p>De AMD-processor presteerde bijzonder goed in multimodale visie-taken, waarbij complexe visuele input tot 7 keer sneller werd verwerkt in IBM Granite Vision 3.2 3B en 6 keer sneller in Google Gemma 3 12B in vergelijking met de Intel-chip. De ondersteuning van AMD voor de technologie Variable Graphics Memory maakt het mogelijk om tot 96 GB geheugen als VRAM toe te wijzen vanuit systemen met een unifieerbaar geheugen van maximaal 128 GB, wat op zijn beurt de implementatie van moderne taalmodellen zoals Google Gemma 3 27B Vision mogelijk maakt.<\/p>\n<p>De voordelen van de AMD-processorprestaties ten opzichte van de concurrent zijn ook zichtbaar in praktische AI-toepassingen, zoals de analyse van medische beelden en hulp bij codering met behulp van zeer nauwkeurige 6-bits kwantisatie in het DeepSeek R1 Distill Qwen 32B-model.<\/p>\n<p><strong>Bronnen:<\/strong><\/p>\n<ul class=\"related\">\n<li><noindex><a rel=\"nofollow\" href=\"https:\/\/www.techpowerup.com\/\" target=\"_blank\" title=\"TechPowerUp\">TechPowerUp<\/a><\/noindex><\/li>\n<li><noindex><a rel=\"nofollow\" href=\"https:\/\/community.amd.com\/\" target=\"_blank\" title=\"AMD Community\">AMD Community<\/a><\/noindex><\/li>\n<\/ul>\n<p> \t           \t  <center>     <center>    <\/center>     <center>   <\/center>     <\/center>  \t\t\t \t\t\t\t<center> \t\t\t\t\t\t\t\t<\/center><br \/>Bron: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/3dnews.ru\/1119872\">3dnews.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041d\u043e\u0432\u0435\u0439\u0448\u0438\u0439 \u0444\u043b\u0430\u0433\u043c\u0430\u043d\u0441\u043a\u0438\u0439 \u043c\u043e\u0431\u0438\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 AMD Ryzen AI Max+ 395 \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u0430 Strix Halo \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0434\u043e 12 \u0440\u0430\u0437 \u0431\u043e\u043b\u0435\u0435 \u0432\u044b\u0441\u043e\u043a\u0443\u044e \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432 \u0440\u0430\u0431\u043e\u0442\u0435 \u0441 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u043c\u0438 \u0431\u043e\u043b\u044c\u0448\u0438\u043c\u0438 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u043c\u0438 \u043c\u043e\u0434\u0435\u043b\u044f\u043c\u0438 \u0418\u0418, \u0447\u0435\u043c \u0447\u0438\u043f\u044b Intel Lunar Lake. \u041e\u0431 \u044d\u0442\u043e\u043c AMD \u0441\u043e\u043e\u0431\u0449\u0438\u043b\u0430 \u0432 \u0441\u0432\u043e\u0451\u043c \u043e\u0444\u0438\u0446\u0438\u0430\u043b\u044c\u043d\u043e\u043c \u0431\u043b\u043e\u0433\u0435, \u043f\u043e\u0434\u0435\u043b\u0438\u0432\u0448\u0438\u0441\u044c \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u044e\u0449\u0438\u043c\u0438 \u0434\u0438\u0430\u0433\u0440\u0430\u043c\u043c\u0430\u043c\u0438. \u0411\u043b\u0430\u0433\u043e\u0434\u0430\u0440\u044f 16 \u0432\u044b\u0447\u0438\u0441\u043b\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c \u044f\u0434\u0440\u0430\u043c Zen 5, 40 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u0431\u043b\u043e\u043a\u0430\u043c RDNA 3.5, \u0430 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":122457,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-122456","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.4 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041d\u043e\u0432\u0435\u0439\u0448\u0438\u0439 \u0444\u043b\u0430\u0433\u043c\u0430\u043d\u0441\u043a\u0438\u0439 \u043c\u043e\u0431\u0438\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 AMD Ryzen AI Max+ 395 \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u0430 Strix Halo \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0434\u043e 12 \u0440\u0430\u0437 \u0431\u043e\u043b\u0435\u0435 \u0432\u044b\u0441\u043e\u043a\u0443\u044e \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432 \u0440\u0430\u0431\u043e\u0442\u0435 \u0441 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u043c\u0438 \u0431\u043e\u043b\u044c\u0448\u0438\u043c\u0438 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u043c\u0438 \u043c\u043e\u0434\u0435\u043b\u044f\u043c\u0438 \u0418\u0418, \u0447\u0435\u043c \u0447\u0438\u043f\u044b Intel Lunar.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/nl\/blog\/news\/amd-pohvastalas-chto-ryzen-ai-max-395-do-12-raz-bystree-v-rabote-s-ii-chem-pryamoj-konkurent-ot-intel\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.4\" \/>\n\t\t<meta property=\"og:locale\" content=\"nl_NL\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47AMD \u043f\u043e\u0445\u0432\u0430\u0441\u0442\u0430\u043b\u0430\u0441\u044c, \u0447\u0442\u043e Ryzen AI Max+ 395 \u0434\u043e 12 \u0440\u0430\u0437 \u0431\u044b\u0441\u0442\u0440\u0435\u0435 \u0432 \u0440\u0430\u0431\u043e\u0442\u0435 \u0441 \u0418\u0418, \u0447\u0435\u043c \u043f\u0440\u044f\u043c\u043e\u0439 \u043a\u043e\u043d\u043a\u0443\u0440\u0435\u043d\u0442 \u043e\u0442 Intel | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041d\u043e\u0432\u0435\u0439\u0448\u0438\u0439 \u0444\u043b\u0430\u0433\u043c\u0430\u043d\u0441\u043a\u0438\u0439 \u043c\u043e\u0431\u0438\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 AMD Ryzen AI Max+ 395 \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u0430 Strix Halo \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0434\u043e 12 \u0440\u0430\u0437 \u0431\u043e\u043b\u0435\u0435 \u0432\u044b\u0441\u043e\u043a\u0443\u044e \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432 \u0440\u0430\u0431\u043e\u0442\u0435 \u0441 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u043c\u0438 \u0431\u043e\u043b\u044c\u0448\u0438\u043c\u0438 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u043c\u0438 \u043c\u043e\u0434\u0435\u043b\u044f\u043c\u0438 \u0418\u0418, \u0447\u0435\u043c \u0447\u0438\u043f\u044b Intel Lunar.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/nl\/blog\/news\/amd-pohvastalas-chto-ryzen-ai-max-395-do-12-raz-bystree-v-rabote-s-ii-chem-pryamoj-konkurent-ot-intel\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2025-03-18T06:22:21+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2025-03-18T06:22:21+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47 AMD heeft geprezen dat de Ryzen AI Max+ 395 tot 12 keer sneller is in AI-toepassingen dan de directe concurrent van Intel | ProHoster","description":"De nieuwste vlaggenschip mobiele processor AMD Ryzen AI Max+ 395 van de Strix Halo-serie biedt tot 12 keer hogere prestaties bij het werken met verschillende grote taalmodellen van AI in vergelijking met Intel Lunar-chips.","canonical_url":"https:\/\/prohoster.info\/nl\/blog\/news\/amd-pohvastalas-chto-ryzen-ai-max-395-do-12-raz-bystree-v-rabote-s-ii-chem-pryamoj-konkurent-ot-intel","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"nl_NL","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47AMD \u043f\u043e\u0445\u0432\u0430\u0441\u0442\u0430\u043b\u0430\u0441\u044c, \u0447\u0442\u043e Ryzen AI Max+ 395 \u0434\u043e 12 \u0440\u0430\u0437 \u0431\u044b\u0441\u0442\u0440\u0435\u0435 \u0432 \u0440\u0430\u0431\u043e\u0442\u0435 \u0441 \u0418\u0418, \u0447\u0435\u043c \u043f\u0440\u044f\u043c\u043e\u0439 \u043a\u043e\u043d\u043a\u0443\u0440\u0435\u043d\u0442 \u043e\u0442 Intel | ProHoster","og:description":"\u041d\u043e\u0432\u0435\u0439\u0448\u0438\u0439 \u0444\u043b\u0430\u0433\u043c\u0430\u043d\u0441\u043a\u0438\u0439 \u043c\u043e\u0431\u0438\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 AMD Ryzen AI Max+ 395 \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u0430 Strix Halo \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0434\u043e 12 \u0440\u0430\u0437 \u0431\u043e\u043b\u0435\u0435 \u0432\u044b\u0441\u043e\u043a\u0443\u044e \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432 \u0440\u0430\u0431\u043e\u0442\u0435 \u0441 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u043c\u0438 \u0431\u043e\u043b\u044c\u0448\u0438\u043c\u0438 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u043c\u0438 \u043c\u043e\u0434\u0435\u043b\u044f\u043c\u0438 \u0418\u0418, \u0447\u0435\u043c \u0447\u0438\u043f\u044b Intel Lunar.","og:url":"https:\/\/prohoster.info\/nl\/blog\/news\/amd-pohvastalas-chto-ryzen-ai-max-395-do-12-raz-bystree-v-rabote-s-ii-chem-pryamoj-konkurent-ot-intel","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2025-03-18T06:22:21+00:00","article:modified_time":"2025-03-18T06:22:21+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"122456","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-23 11:20:20","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2026-01-23 11:20:20","updated":"2026-01-23 11:20:20","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/posts\/122456","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/comments?post=122456"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/posts\/122456\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/media\/122457"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/media?parent=122456"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/categories?post=122456"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/nl\/wp-json\/wp\/v2\/tags?post=122456"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}