{"id":10517,"date":"2026-08-13T09:00:00","date_gmt":"2026-08-13T13:00:00","guid":{"rendered":"https:\/\/blogs.swarthmore.edu\/its\/?p=10517"},"modified":"2026-08-11T17:10:47","modified_gmt":"2026-08-11T21:10:47","slug":"running-open-source-llms-on-firebird","status":"publish","type":"post","link":"https:\/\/blogs.swarthmore.edu\/its\/2026\/08\/13\/running-open-source-llms-on-firebird\/","title":{"rendered":"Running Open-Source LLMs on Firebird"},"content":{"rendered":"\n<p>Firebird can now <a href=\"https:\/\/kb.swarthmore.edu\/wiki\/Running_Ollama_and_LLMs_on_Firebird\">host and run open-source large language models directly on the cluster using Ollama<\/a>, a tool that makes it straightforward to pull down a model (and Ollama has <a href=\"https:\/\/ollama.com\/search\">LOTS of models<\/a>!) and start working with it. Anyone with a Firebird account can spin up a capable model and run it against the cluster&#8217;s GPUs. Models run entirely locally; nothing you send to the model ever leaves Firebird.<\/p>\n\n\n\n<p>Options for interacting with such models are essentially endless and are similar to ways in which you might use existing AI tools (Claude, Gemini, ChatGPT, etc.), such as:<\/p>\n\n\n\n<p><strong>Working with sensitive or restricted text.<\/strong> Because everything stays on the cluster, you can work with material you would never paste into an outside service, such as unpublished manuscripts, licensed corpora, or data covered by a use agreement. Summarizing, classifying, or coding that kind of text is now something you can do without the data leaving a controlled environment.<\/p>\n\n\n\n<p><strong>Large-scale text processing.<\/strong> It is possible to use models as part of batch jobs with Slurm. Instead of processing documents one at a time or in small batches, you can queue up thousands and extract structured fields, label, translate, or summarize in bulk.<\/p>\n\n\n\n<p><strong>Teaching and AI literacy.<\/strong> A professor can easily give an entire class access to models. And because the models are open, students can look under the hood: compare different models, adjust how they run, and study how they actually behave rather than treating them as a black box.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Firebird can now host and run open-source large language models directly on the cluster using Ollama, a tool that makes it straightforward to pull down a model (and Ollama has LOTS of models!) and start working with it. Anyone with &hellip; <a href=\"https:\/\/blogs.swarthmore.edu\/its\/2026\/08\/13\/running-open-source-llms-on-firebird\/\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">Running Open-Source LLMs on Firebird<\/span><\/a><\/p>\n","protected":false},"author":77,"featured_media":10518,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[2,435,450,357,125,430],"tags":[61,344,90,128,201],"class_list":{"0":"post-10517","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","6":"hentry","7":"category-academic-technology","8":"category-artificial-intelligence","9":"category-data-science","10":"category-high-performance-computing","11":"category-open-source","12":"category-research","13":"tag-academic-technology","14":"tag-ai","15":"tag-featured","16":"tag-high-performance-computing","17":"tag-research","19":"fallback-thumbnail"},"jetpack_featured_media_url":"https:\/\/blogs.swarthmore.edu\/its\/wp-content\/uploads\/2026\/08\/Firefly-1-scaled.jpg","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/ph2nPL-2JD","_links":{"self":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts\/10517","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/users\/77"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/comments?post=10517"}],"version-history":[{"count":1,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts\/10517\/revisions"}],"predecessor-version":[{"id":10519,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/posts\/10517\/revisions\/10519"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/media\/10518"}],"wp:attachment":[{"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/media?parent=10517"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/categories?post=10517"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.swarthmore.edu\/its\/wp-json\/wp\/v2\/tags?post=10517"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}