GitHub · C++
Helldez/BigMoeOnEdge
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
- Stars
- 1,033
- Forks
- 107
- Stars gained in 24 hours
- +23
- Forks gained in 24 hours
- +4
Topics: android, cpp, edge-ai, gemma, gguf, inference, llama-cpp, llm, mixture-of-experts, moe
Latest data point: Nov 20, 2026 · 1,033 stars · 107 forks