Tencent/AngelSlim

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

70
/ 100
Verified

When deploying large language or vision models, this tool helps you shrink their size and speed them up without losing accuracy. It takes your pre-trained large AI model and applies various compression techniques to produce a smaller, faster version suitable for efficient real-world use. AI engineers and MLOps specialists who need to run large models on resource-constrained hardware or in production environments will find this particularly useful.

536 stars. Actively maintained with 18 commits in the last 30 days. Available on PyPI.

Use this if you need to optimize large AI models (LLMs, VLMs) for faster inference, reduced memory footprint, or deployment on edge devices.

Not ideal if you are still in the early stages of model development and not yet focused on deployment efficiency.

AI model deployment Large language model optimization On-device AI MLOps Vision language model deployment
Maintenance 17 / 25
Adoption 10 / 25
Maturity 24 / 25
Community 19 / 25

How are scores calculated?

Stars

536

Forks

68

Language

Python

License

Last pushed

Mar 12, 2026

Commits (30d)

18

Dependencies

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Tencent/AngelSlim"

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