OneComp

Overview

OneComp is an open-source Python package for compressing large language models. It provides algorithms to reduce model size while preserving performance, enabling deployment on resource-constrained environments.

Best for

Best for
Developers needing to shrink LLMs for deployment on limited hardware

Use cases

• Reduce LLM memory footprint for edge deployment
• Speed up inference by compressing model weights
• Quantize or prune models for cost-efficient serving

Notes

OneComp is an open-source Python package for compressing large language models. It provides algorithms to reduce model size while preserving performance, enabling deployment on resource-constrained environments.

379 stars on GitHub. Last updated 2026-05-28. Licensed MIT.

Use cases

• Reduce LLM memory footprint for edge deployment
• Speed up inference by compressing model weights
• Quantize or prune models for cost-efficient serving

Pros

• Open source with permissive license
• Lightweight and easy to integrate into Python workflows
• Targets practical compression for production use

Cons

• Limited documentation and examples beyond basic usage
• Small community (379 stars) may mean slower updates
• Compression techniques may not cover all model architectures

Indexed from awesome-llmops and enriched against its public facts.