FreeAIRepo
Inference & serving

swellweb/reame

CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accurate than tuning the engine. MIT, benchmarks and failures in

Really freeCommercial OK · MITCPU only OKC++
Stars
114
Forks
10
Open issues
5
Last push
14d ago

About reame

reame is a free, open-source AI inference tool by swellweb, written mainly in C++. CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accurate than tuning the engine. MIT, benchmarks and failures in. It has 114 GitHub stars and 10 forks, and was last updated 14d ago. It's released under the MIT license, a standard open-source license. According to the project, it runs on a regular CPU without a GPU.

License
MIT
Commercial use
Commercial OK
Language
C++
Stars
114
Last update
14d ago
Runs on Mac
Not stated
GPU
Not needed (runs on CPU)
Paid API key
Not required
Self-hostable
Not stated

Similar free tools

All Inference & serving tools →

reame FAQ

Can I use reame commercially?

Yes. MIT is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.

Is reame free?

Yes. reame is open source and free to use. It's released under the MIT license, a standard open-source license.

Does reame run on a Mac?

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

Does reame need a GPU?

No. According to the project, reame runs on a regular CPU.

Is reame still maintained?

Yes. It was last updated 14d ago and has 5 open issues on GitHub.

What are alternatives to reame?

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

Related topics