uncSoft/anubis-oss

Local LLM Testing & Benchmarking for Apple Silicon

37
/ 100
Emerging

Anubis helps developers, researchers, or anyone experimenting with large language models (LLMs) understand how different models perform on their Apple Silicon Mac. It takes local LLMs (like those run with Ollama or LM Studio) and provides detailed, real-time metrics on inference speed, CPU/GPU usage, and power consumption. The output is comprehensive performance data, charts, and comparison reports, allowing you to easily see which LLM runs best on your specific hardware configuration.

Use this if you are developing with or evaluating local large language models on an Apple Silicon Mac and need to systematically benchmark their performance and resource usage.

Not ideal if you are solely looking for a chat interface for LLMs or if you are not using an Apple Silicon Mac.

LLM development machine learning engineering performance testing model evaluation Apple Silicon optimization
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 8 / 25

How are scores calculated?

Stars

68

Forks

4

Language

Swift

License

GPL-3.0

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/uncSoft/anubis-oss"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.