inferssd
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
inferssd launched on 22 October 2026. It ranked #115 on Daily Launch on 16 November 2026 with a Launch Score of 9, from +38 stars on 16 Nov on GitHub. It moved down 38 places from the day before.
What is inferssd?
Run models larger than your RAM or VRAM. InferSSD builds on llama.cpp to run large mixture-of-experts (MoE) models from SSD, using standard GGUF files, with browser chat and an OpenAI-compatible API. It supports DeepSeek-V4.1-Flash-1017, Muse-Spark-Open, Qwen3.6-35B-A3B and Qwen3.8 Flash Next, plus ordinary RAM inference for Gemma4 E4B.
From its README on GitHub
inferssd is a repo by wici-ai on GitHub. It is written in C++ and released under the Apache-2.0 license.
How to get inferssd
Get it from its repository on GitHub.