C++ · Apache-2.0
wici-ai/inferssd
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
★ 319
Stars
51 forks · 14 open issues
+23/day
Growth · lifetime avg
Average since the repo was created — it is young enough that this still describes now. Not a recent-week figure.
48.5
Momentum / 100
see the breakdown below
16d ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 26.3 | +23/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 7.3 | 319 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 48.5 | sum of the above |
Detail
| Topics | apple-siliconcudaggufinferencellama-cppllmmetalmixture-of-expertsssd |
| Matched on | LLM & Inference (llm) |
| Short window | no snapshot 5–10 days old yet |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 22.68 stars/day over 14 days |
| First seen here | 2026-11-02 |
| Last read | 2d ago |