{"id":54732,"date":"2025-08-08T14:53:14","date_gmt":"2025-08-08T14:53:14","guid":{"rendered":"https:\/\/www.newsbeep.com\/ca\/54732\/"},"modified":"2025-08-08T14:53:14","modified_gmt":"2025-08-08T14:53:14","slug":"openai-intros-two-open-weight-language-models-that-can-run-on-consumer-gpus-optimized-to-run-on-devices-with-just-16gb-of-memory","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ca\/54732\/","title":{"rendered":"OpenAI intros two open-weight language models that can run on consumer GPUs \u2014 optimized to run on devices with just 16GB of memory"},"content":{"rendered":"

OpenAI has developed a pair of new open-weight language models optimized for consumer GPUs. In a blog post<\/a>, OpenAI announced “gpt-oss-120b” and “gpt-oss-20b”, the former designed to run on a single 80GB GPU and the latter optimized to run on edge devices with just 16GB of memory.<\/p>\n

Both models take advantage of a Transformer using the mixture-of-experts model, a model that was popularized with DeepSeek R1<\/a>. Despite gpt-oss-120b and 20b’s design focus towards consumer GPUs, both support up to 131,072 context lengths, the longest available for local inference. gpt-oss-120b activates 5.1 billion parameters per token, and gpt-oss-20b activates 3.6 billion parameters per token. Both models use alternating dense and locally banded sparse attention patterns and use grouped multi-query attention with a group size of 8.<\/p>\n

Both models take advantage of a Chain-of-Thought reasoning architecture with a mixed focus on reasoning, efficiency, and real-world usability. The two gpt-oss models are also the first open-weight language models since GPT-2. Open AI models are similar to open-source software, providing easier accessibility for developers. OpenAI opted to make its two latest models open-source to boost adoption in emerging markets and other sectors that might lack the capability to adopt its proprietary models.<\/p>\n

You may like<\/p>\n

The gpt-oss-120b model allegedly achieves nearly identical performance with OpenAI’s outgoing o4-mini language model on core reasoning benchmarks<\/a> but is capable of doing all this on a single 80GB GPU. gpt-oss-20b delivers similar performance to OpenAI’s outgoing o3-mini language model while being capable of running on devices with just 16GB of memory.<\/p>\n

In evaluations OpenAI conducted, gpt-oss-120b outperformed o3-mini and matched or exceeded o4-mini in competition coding, general problem solving, and tool calling. However, 120b was also capable of outperforming o4-mini in health-related queries and competition mathematics. gpt-oss-20b was able to perform the exact same benchmarking behavior against o3-mini.<\/p>\n

The two new OpenAI models are available to use now under the Apache 2.0 open-source license. OpenAI has partnered with a plethora of companies to support its latest models on a variety of platforms, including ONNX Runtime, Azure, AWS, and Ollama.<\/p>\n

Get Tom’s Hardware’s best news and in-depth reviews, straight to your inbox.<\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI has developed a pair of new open-weight language models optimized for consumer GPUs. In a blog post,…\n","protected":false},"author":2,"featured_media":54733,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[62,276,277,49,48,61],"class_list":["post-54732","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-ca","tag-canada","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/54732","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/comments?post=54732"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/54732\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media\/54733"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media?parent=54732"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/categories?post=54732"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/tags?post=54732"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}