inferssd
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Run large AI models that exceed your computer's memory by streaming them from your SSD.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeRun models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
inferssd has 1.1k stars on GitHub. It has been forked 80 times. inferssd is written mainly in C++. It has been in active development since 2026. inferssd is available under the Apache-2.0 license. Its main topics are apple-silicon, cuda, gguf, inference.
What is inferssd?
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Is inferssd open source?
inferssd is an open-source project. It is released under the Apache-2.0 license.
Is inferssd free?
Yes. inferssd is free and open source — you can use, modify and self-host it.
What license does inferssd use?
inferssd is available under the Apache-2.0 license.
What language is inferssd written in?
inferssd is written mainly in C++.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/wici-ai-inferssd.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.