FreeAIRepo
Inference & serving

RustingStudio/RustingStrata

Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.cpp prefill and decode on a 12 GB RTX 3060.

No licenseRust

Rising: +33 stars in the last 2 days, created 28d ago

  • 130stars
  • 16forks
  • 7open issues
  • updated today

About RustingStrata

RustingStrata is a free, open-source AI inference tool by RustingStudio, written mainly in Rust. Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.cpp prefill and decode on a 12 GB RTX 3060. It has 130 GitHub stars and 16 forks, and was last updated today. GitHub doesn't detect a standard license, so check the repository before using it commercially.

Similar free tools

All Inference & serving tools →

RustingStrata FAQ

Can I use RustingStrata commercially?

Unclear. No license was detected, which legally means all rights are reserved. Ask the author before using it commercially. This is a plain-English summary, not legal advice.

Is RustingStrata free?

Yes. RustingStrata is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.

Does RustingStrata run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does RustingStrata need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is RustingStrata still maintained?

Yes. It was last updated today and has 7 open issues on GitHub.

What are alternatives to RustingStrata?

Similar free, open-source tools include llama.cpp, llm-action, vllm, OpenLLM.

Related topics

Maintain RustingStrata? Add a FreeAIRepo badge to your README
Featured on FreeAIRepo
[![Featured on FreeAIRepo](https://www.freeairepo.com/badge/RustingStudio/RustingStrata.svg)](https://www.freeairepo.com/repo/RustingStudio/RustingStrata)