{"id":672527,"date":"2025-05-30T11:28:31","date_gmt":"2025-05-30T08:28:31","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/deepseeks-distilled-new-r1-ai-model-can-run-on-a-single-gpu\/"},"modified":"2025-05-30T11:28:31","modified_gmt":"2025-05-30T08:28:31","slug":"deepseeks-distilled-new-r1-ai-model-can-run-on-a-single-gpu","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/deepseeks-distilled-new-r1-ai-model-can-run-on-a-single-gpu\/","title":{"rendered":"DeepSeek’s distilled new R1 AI model can run on a single GPU"},"content":{"rendered":"
\n

DeepSeek\u2019s updated R1 reasoning AI model might be getting the bulk of the AI community\u2019s attention this week. But the Chinese AI lab also released a smaller, \u201cdistilled\u201d version of its new R1, DeepSeek-R1-0528-Qwen3-8B, that DeepSeek claims beats comparably sized models on certain benchmarks.<\/p>\n

The smaller updated R1, which was built using the Qwen3-8B model Alibaba launched in May as a foundation, performs better than Google\u2019s Gemini 2.5 Flash on AIME 2025, a collection of challenging math questions. <\/p>\n

DeepSeek-R1-0528-Qwen3-8B also nearly matches Microsoft\u2019s recently released Phi 4 reasoning plus model on another math skills test, HMMT.<\/p>\n

So-called distilled models like DeepSeek-R1-0528-Qwen3-8B are general<\/a>ly less capable than their full-sized counterparts. On the plus side, they\u2019re far less computationally demanding. According<\/a> to the cloud platform NodeShift, Qwen3-8B requires a GPU with 40GB-80GB of RAM to run (e.g., an Nvidia H100). The full-sized new R1 needs around a dozen 80GB GPUs<\/a>.<\/p>\n

DeepSeek trained DeepSeek-R1-0528-Qwen3-8B by taking text generated by the updated R1 and using it to fine-tune Qwen3-8B. In a dedicated web page for the model on the AI dev platform Hugging Face, DeepSeek describes DeepSeek-R1-0528-Qwen3-8B as \u201cfor both academic research on reasoning models and industrial development focused on small-scale models.\u201d<\/p>\n

DeepSeek-R1-0528-Qwen3-8B is available under a permissive MIT license, meaning it can be used commercially without restriction. Several hosts, including LM Studio<\/a>, already offer the model through an API.<\/p>\n<\/div>\n

If you liked the article, do not forget to share it with your friends. Follow us on\u00a0Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n

\n

If you want to read more like this article, you can visit our Technology<\/a><\/span> category.<\/strong><\/p>\n<\/blockquote>\n

Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

DeepSeek\u2019s updated R1 reasoning AI model might be getting the bulk of the AI community\u2019s attention this week. But the Chinese AI lab also released a smaller, \u201cdistilled\u201d version of its new R1, DeepSeek-R1-0528-Qwen3-8B, that DeepSeek claims beats comparably sized models on certain benchmarks. The smaller updated R1, which was built using the Qwen3-8B model…<\/p>\n","protected":false},"author":1,"featured_media":672528,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/01\/GettyImages-2196223480.jpg?resize=1200,825","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[77337,4973,153752],"class_list":["post-672527","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology","tag-ai","tag-china","tag-deepseek"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/672527","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=672527"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/672527\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/672528"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=672527"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=672527"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=672527"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}