{"version":"1.0","type":"card","id":"028e175c-35b3-4ffe-8894-fb23b81c58a8","url":"https://stacklist.com/card/028e175c-35b3-4ffe-8894-fb23b81c58a8","title":"Fast MTP Models and llama.cpp Recommendation","source_url":"https://x.com/tmophoto/status/2056407696363176012","note":"This page discusses the impressive speed of new MTP models and recommends installing llama.cpp for optimal performance. The author shares their experience using it on dual 3090 GPUs.","image":{"url":"https://ucarecdn.com/eb2d790f-518c-4e42-9515-4b105a7e414f/","alt":"Fast MTP Models and llama.cpp Recommendation","width":1200,"height":1200},"stack":{"id":"4d7ef7fd-5f42-4150-adcc-f1e3197f7cbf","title":"X Bookmarks","url":"https://stacklist.com/c/technology/stack/4d7ef7fd-5f42-4150-adcc-f1e3197f7cbf"},"created_at":"2026-07-29T02:57:55.214Z","updated_at":null,"aco":null,"_links":{"self":"/api/public/card/028e175c-35b3-4ffe-8894-fb23b81c58a8.json","html":"https://stacklist.com/card/028e175c-35b3-4ffe-8894-fb23b81c58a8","md":"/api/public/card/028e175c-35b3-4ffe-8894-fb23b81c58a8.md","stack_json":"/api/public/stack/4d7ef7fd-5f42-4150-adcc-f1e3197f7cbf.json"}}