[{"data":1,"prerenderedAt":105},["ShallowReactive",2],{"run-llm-without-gpu":3},{"llama-cpp":4,"ollama":40,"llamafile":74},{"id":5,"slug":5,"name":6,"url":7,"curatedDescription":8,"category":9,"section":14,"repo":18,"media":31,"source":34,"sync":38},"llama-cpp","llama.cpp","https://github.com/ggml-org/llama.cpp","Pure C/C++ inference engine with GGUF format support. The gold standard for CPU/GPU/Apple Silicon on-device running. Includes llama-server for OpenAI-compatible API. Now at 100K+ stars.",{"id":10,"slug":10,"title":11,"navTitle":12,"order":13},"inference-engines-and-serving","Inference Engines & Serving","Serving",3,{"id":15,"slug":15,"title":16,"order":17},"local-on-device-inference","Local / On-device Inference",1,{"host":19,"owner":20,"name":6,"fullName":21,"stars":22,"license":23,"primaryLanguage":24,"homepage":25,"topics":26,"description":28,"pushedAt":29,"archived":30,"fork":30},"github","ggml-org","ggml-org/llama.cpp",114610,"MIT","C++","https://llama.app",[27],"ggml","LLM inference in C/C++","2026-06-04T17:13:26Z",false,{"iconUrl":32,"avatarUrl":33},null,"https://avatars.githubusercontent.com/u/134263123?v=4",{"readmeUrl":35,"readmeLine":36,"sourceHash":37},"https://github.com/alvinreal/awesome-opensource-ai/blob/main/README.md",268,"51f68a2074861f18f5695e7f6da908d1029b2790ebd927f8be45e93281e61908",{"lastSyncedAt":39},"2026-07-11T12:01:01.385Z",{"id":41,"slug":41,"name":42,"url":43,"curatedDescription":44,"category":45,"section":46,"repo":47,"media":69,"source":71,"sync":73},"ollama","Ollama","https://github.com/ollama/ollama","Dead-simple local LLM runner with a one-line install, model registry, and OpenAI-compatible API.",{"id":10,"slug":10,"title":11,"navTitle":12,"order":13},{"id":15,"slug":15,"title":16,"order":17},{"host":19,"owner":41,"name":41,"fullName":48,"stars":49,"license":23,"primaryLanguage":50,"homepage":51,"topics":52,"description":67,"pushedAt":68,"archived":30,"fork":30},"ollama/ollama",173169,"Go","https://ollama.com",[53,54,55,56,57,58,59,60,61,62,63,64,65,41,66],"deepseek","gemma","gemma3","glm","go","golang","gpt-oss","llama","llama3","llm","llms","minimax","mistral","qwen","Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.","2026-06-04T18:05:37Z",{"iconUrl":32,"avatarUrl":70},"https://avatars.githubusercontent.com/u/151674099?v=4",{"readmeUrl":35,"readmeLine":72,"sourceHash":37},269,{"lastSyncedAt":39},{"id":75,"slug":75,"name":75,"url":76,"curatedDescription":77,"category":78,"section":79,"repo":83,"media":100,"source":102,"sync":104},"llamafile","https://github.com/mozilla-ai/llamafile","Mozilla's single-file distributable LLM solution. Bundle model weights, inference engine, and runtime into one portable executable that runs on six OSes without installation.",{"id":10,"slug":10,"title":11,"navTitle":12,"order":13},{"id":80,"slug":80,"title":81,"order":82},"high-performance-serving-and-api-servers","High-performance Serving & API Servers",2,{"host":19,"owner":84,"name":75,"fullName":85,"stars":86,"license":87,"primaryLanguage":24,"homepage":88,"topics":89,"description":98,"pushedAt":99,"archived":30,"fork":30},"mozilla-ai","mozilla-ai/llamafile",24654,"NOASSERTION","https://docs.mozilla.ai/llamafile",[90,91,5,92,93,94,95,96,97],"cross-platform","gguf","local-ai","local-inference","local-llm","open-source-ai","single-file-executable","speech-to-text","Distribute and run LLMs with a single file.","2026-06-04T12:00:25Z",{"iconUrl":32,"avatarUrl":101},"https://avatars.githubusercontent.com/u/129804596?v=4",{"readmeUrl":35,"readmeLine":103,"sourceHash":37},299,{"lastSyncedAt":39},1783804186677]