{"id":239999,"date":"2026-06-30T07:31:12","date_gmt":"2026-06-30T12:31:12","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2026\/06\/we-are-introducing-and-open-sourcing-longcat-2-0-a-large-scale-moe-language-model-with-1-6-trillion-total-parameters-and-48-billion-activated-per-token"},"modified":"2026-06-30T07:31:12","modified_gmt":"2026-06-30T12:31:12","slug":"we-are-introducing-and-open-sourcing-longcat-2-0-a-large-scale-moe-language-model-with-1-6-trillion-total-parameters-and-48-billion-activated-per-token","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2026\/06\/we-are-introducing-and-open-sourcing-longcat-2-0-a-large-scale-moe-language-model-with-1-6-trillion-total-parameters-and-48-billion-activated-per-token","title":{"rendered":"We are introducing and open sourcing LongCat-2.0, a large-scale MoE language model with 1.6 trillion total parameters and ~48 billion activated per token \u2014"},"content":{"rendered":"<p style=\"padding-right: 20px\"><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/we-are-introducing-and-open-sourcing-longcat-2-0-a-large-scale-moe-language-model-with-1-6-trillion-total-parameters-and-48-billion-activated-per-token2.jpg\"><\/a><\/p>\n<p>We are introducing and open sourcing, a large-scale MoE language model with <strong>1.6 trillion total parameters<\/strong> and ~48 billion activated per token \u2014 a substantial step up from previous LongCat models, accompanied by several architectural improvements.<\/p>\n<p>Both the full training run and the large-scale deployment are built entirely on <strong>AI ASIC superpods<\/strong>. Pretraining spans millions of accelerator-days across more than 35 trillion tokens, with no rollbacks or irrecoverable loss spikes \u2014 demonstrating that we have the capability to conduct frontier-scale training on alternative hardware platforms.<\/p>\n<p>To strengthen the model on long-horizon tasks, we introduce LongCat Sparse Attention and train on hundreds of billions of tokens of <strong>1M-context<\/strong> data. Together with dedicated post-training, this gives strong performance on coding and agentic tasks.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We are introducing and open sourcing, a large-scale MoE language model with 1.6 trillion total parameters and ~48 billion activated per token \u2014 a substantial step up from previous LongCat models, accompanied by several architectural improvements. Both the full training run and the large-scale deployment are built entirely on AI ASIC superpods. Pretraining spans millions [\u2026]<\/p>\n","protected":false},"author":709,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-239999","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/239999","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/709"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=239999"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/239999\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=239999"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=239999"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=239999"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}