{"id":1467,"date":"2026-10-12T18:20:17","date_gmt":"2026-10-12T18:20:17","guid":{"rendered":"https:\/\/blog.faktor0.de\/?p=1467"},"modified":"2026-10-12T19:18:50","modified_gmt":"2026-10-12T19:18:50","slug":"llama-cpp","status":"publish","type":"post","link":"https:\/\/blog.faktor0.de\/?p=1467","title":{"rendered":"llama.cpp &#8211; text to text KI"},"content":{"rendered":"<p>llama.cpp Homepage:<br \/>\n<a href=\"https:\/\/github.com\/ggml-org\/llama.cpp\">https:\/\/github.com\/ggml-org\/llama.cpp<\/a><\/p>\n<p>Installieren auf MacOS:<br \/>\n<code>brew install llama.cpp<\/code><\/p>\n<p>Server starten mit Modell:<br \/>\n<code>llama serve -hf ggml-org\/Qwen3.5-0.8B-GGUF<\/code><\/p>\n<p>Der Server ist erreichbar unter:<br \/>\n<a href=\"http:\/\/127.0.0.1:8080\" target=\"_blank\">http:\/\/127.0.0.1:8080<\/a><\/p>\n<p>Die Modelle werden mit dem Parameter <code>-hf<\/code> von <a href=\"https:\/\/hugginface.co\" target=\"_blank\">https:\/\/hugginface.co<\/a> heruntergeladen und gespeichert unter<br \/>\n<code>~\/.cache\/huggingface\/hub <\/code><\/p>\n<p>Modelle f\u00fcr llama.cpp finden sich unter:<br \/>\n<a href=\"https:\/\/huggingface.co\/ggml-org\/models#repos\">https:\/\/huggingface.co\/ggml-org\/models#repos<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>llama.cpp Homepage: https:\/\/github.com\/ggml-org\/llama.cpp Installieren auf MacOS: brew install llama.cpp Server starten mit Modell: llama serve -hf ggml-org\/Qwen3.5-0.8B-GGUF Der Server ist erreichbar unter: http:\/\/127.0.0.1:8080 Die Modelle werden mit dem Parameter -hf von https:\/\/hugginface.co heruntergeladen und gespeichert unter ~\/.cache\/huggingface\/hub Modelle f\u00fcr llama.cpp finden sich unter: https:\/\/huggingface.co\/ggml-org\/models#repos<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,16],"tags":[],"class_list":["post-1467","post","type-post","status-publish","format-standard","hentry","category-programmieren","category-web-programmierung"],"_links":{"self":[{"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=\/wp\/v2\/posts\/1467","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1467"}],"version-history":[{"count":6,"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=\/wp\/v2\/posts\/1467\/revisions"}],"predecessor-version":[{"id":1473,"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=\/wp\/v2\/posts\/1467\/revisions\/1473"}],"wp:attachment":[{"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1467"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1467"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.faktor0.de\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1467"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}