wici-ai/inferssd
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
- Stars621
- LanguageC++
- LicenseApache-2.0
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
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.
These are the tested GGUF files, community conversions of the named model releases. DeepSeek's Q8_0 keeps the official bit widths: routed experts stay native 4-bit MXFP4, and FP8 tensors become 8-bit Q8_0. See weight-format details.
Description and README excerpt from wici-ai/inferssd on GitHub ↗.
wici-ai/inferssd was first seen on GitHub · Rising today on Nov 12, 2026. Since then it has appeared in 149 checks on 3 different days. Its best position was #3 of 30, reached on Nov 13, 23:15 UTC. It dropped off the list after Nov 14, 03:01 UTC.
Position on GitHub · Rising today at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by GitHub.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 14, 03:01 UTC, after 3 days of trending.
#3 on GitHub · Rising today, on Nov 13, 23:15 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 12, 2026 and has been on the list on 3 days (149 checks) since.
Mostly C++; it is licensed under Apache-2.0. It has 621 stars and 73 forks.