MinishLab/model2vec-rs

Official Rust Implementation of Model2Vec

50
/ 100
Established

Compresses sentence transformers into lightweight static embeddings via Model2Vec distillation, supporting f32/f16/i8 weight types from Hugging Face Hub or local paths. Provides both a library API and CLI tool with batch processing and configurable sequence length/batch size parameters. Optimized for inference-only workloads requiring sub-100ms latency on CPU.

161 stars and 2,871 monthly downloads.

No Package No Dependents
Maintenance 10 / 25
Adoption 18 / 25
Maturity 9 / 25
Community 13 / 25

How are scores calculated?

Stars

161

Forks

15

Language

Rust

License

MIT

Last pushed

Feb 05, 2026

Monthly downloads

2,871

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/MinishLab/model2vec-rs"

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