PrunaAI/pruna

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

63
/ 100
Established

This tool helps machine learning engineers and AI developers make their AI models faster, smaller, and more cost-effective. You input your existing, trained AI model (like an LLM or a vision transformer), and it outputs an optimized version that runs more efficiently. It's designed for developers building and deploying AI solutions who need to improve model performance and resource usage.

1,142 stars. Actively maintained with 17 commits in the last 30 days.

Use this if you are a machine learning engineer looking to reduce the inference time, memory footprint, or operational cost of your deployed AI models.

Not ideal if you are an end-user without programming skills or if your primary goal is to train a new AI model from scratch rather than optimize an existing one.

model-optimization AI-deployment machine-learning-engineering resource-management model-efficiency
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

1,142

Forks

85

Language

Python

License

Apache-2.0

Last pushed

Mar 26, 2026

Commits (30d)

17

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PrunaAI/pruna"

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