Helldez/BigMoeOnEdge

BigMoeOnEdge

✅ Recently maintained

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.

704Stars
81Forks
+307-day stars

C++ · Apache-2.0 · Last push 2026-11-02

Official repository & installation ↗
androidcppedge-aiggufinferencellama-cppllmmixture-of-expertsmoeon-device-ai

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-07-062026-11-03
View historical data
DateStars
2026-10-05606
2026-10-06609
2026-10-07611
2026-10-08612
2026-10-09612
2026-10-10612
2026-10-11615
2026-10-12618
2026-10-13621
2026-10-14622
2026-10-15623
2026-10-16626
2026-10-17628
2026-10-18629
2026-10-19633
2026-10-20640
2026-10-21646
2026-10-22649
2026-10-23650
2026-10-24657
2026-10-25661
2026-10-26671
2026-10-27679
2026-10-28681
2026-10-29685
2026-10-30690
2026-10-31695
2026-11-01697
2026-11-02698
2026-11-03704

Get the project

git clone https://github.com/Helldez/BigMoeOnEdge.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

★ 38,386vllm

High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.

★ 96,180litellm

Call 100+ LLM APIs using the OpenAI input/output format.

★ 62,604