nagu-io/CompressX

Compress any LLM to 25% of its size. Open source pipeline using quantization, pruning, and 1-bit QEP.

/ 100

Experimental

No Package No Dependents

Maintenance 13 / 25

Adoption 0 / 25

Maturity 9 / 25

Community 0 / 25

Stars

—

Forks

—

Language

Python

License

MIT

Category

Last pushed

Mar 19, 2026

Commits (30d)

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/nagu-io/CompressX"

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

Higher-rated alternatives

Dicklesworthstone/llm_introspective_compression_and_metacognition

A novel approach for transformer model introspection that enables saving, compressing, and...

zjunlp/LightThinker

[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression