fastembed-rs and finalfusion-rust

These are competitors offering alternative Rust implementations for generating and working with text embeddings, with finalfusion-rust focusing on pre-trained embedding models while fastembed-rs emphasizes speed and includes reranking capabilities.

fastembed-rs
60
Established
finalfusion-rust
40
Emerging
Maintenance 20/25
Adoption 10/25
Maturity 9/25
Community 21/25
Maintenance 0/25
Adoption 17/25
Maturity 9/25
Community 14/25
Stars: 791
Forks: 111
Downloads:
Commits (30d): 6
Language: Rust
License: Apache-2.0
Stars: 105
Forks: 13
Downloads: 3,663
Commits (30d): 0
Language: Rust
License:
No Package No Dependents
Stale 6m No Package No Dependents

About fastembed-rs

Anush008/fastembed-rs

Rust library for vector embeddings and reranking.

Performs inference using ONNX Runtime via the `ort` crate and HuggingFace tokenizers for fast token encoding, enabling synchronous (non-async) embedding generation without external dependencies. Supports 25+ pre-trained text embedding models from BAAI, Sentence Transformers, and others, plus sparse embeddings, image embeddings, and reranking—with quantized variants and optional Candle backend support for advanced models like Qwen3.

About finalfusion-rust

finalfusion/finalfusion-rust

finalfusion embeddings in Rust

Supports multiple vocabulary and storage backends including memory-mapped and product-quantized embeddings for flexible performance/memory tradeoffs, plus cross-format conversion (fastText, word2vec, GloVe). Enables similarity and analogy queries through `ndarray`-backed vector operations, with optional BLAS/LAPACK acceleration for quantized lookups. Integrates with the finalfusion ecosystem for training embeddings via finalfrontier and quantization via the reductive crate.

Scores updated daily from GitHub, PyPI, and npm data. How scores work