{"source":"https://ossradar.net","license":"Free to use with a link back to ossradar.net","generatedAt":"2026-11-16T02:48:20.780Z","repo":{"fullName":"wici-ai/inferssd","url":"https://github.com/wici-ai/inferssd","ossradarUrl":"https://ossradar.net/repo/wici-ai/inferssd","markdownUrl":"https://ossradar.net/repo/wici-ai/inferssd.md","summary":"Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.","description":"Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.","homepage":"https://wici.ai/inferssd","language":"C++","license":"Apache-2.0","category":"Local LLMs","categoryUrl":"https://ossradar.net/category/local-llms","topics":["apple-silicon","cuda","gguf","inference","llama-cpp","llm","metal","mixture-of-experts","ssd"],"stars":1184,"forks":99,"starsGained24h":48,"starsGained7d":813,"estimated":false,"rankToday":190,"rankThisWeek":91,"trackedRepos":450,"createdAt":"2026-10-22T10:40:45Z","pushedAt":"2026-11-15T09:33:50Z","starHistory":[{"date":"2026-11-02","stars":258},{"date":"2026-11-03","stars":290},{"date":"2026-11-04","stars":312},{"date":"2026-11-05","stars":327},{"date":"2026-11-06","stars":346},{"date":"2026-11-07","stars":358},{"date":"2026-11-08","stars":363},{"date":"2026-11-09","stars":371},{"date":"2026-11-10","stars":385},{"date":"2026-11-11","stars":392},{"date":"2026-11-12","stars":632},{"date":"2026-11-13","stars":1068},{"date":"2026-11-14","stars":1118},{"date":"2026-11-15","stars":1179},{"date":"2026-11-16","stars":1184}],"hackerNews":{"stories":1,"topStory":{"title":"Inferssd – Run models larger than RAM or VRAM by streaming MoE experts from SSD","points":1,"comments":0,"date":"2026-10-30","url":"https://news.ycombinator.com/item?id=50308376"}},"alternativesUrl":"https://ossradar.net/alternatives/wici-ai/inferssd","alternatives":["synchopate/llama-modchip","mw00/project-maya","simplexai-labs/PolyStrata","AtomicBot-ai/atomic-agent","huawei-csl/MACaQ"],"badgeUrl":"https://ossradar.net/badge/wici-ai/inferssd"}}