Local runtime · Server engine
Text Embeddings Inference
A Rust-based inference server purpose-built for serving text embedding, sparse embedding, sequence-classification, and reranking models on operator-controlled hardware.
- Maintainer
- Hugging Face
- Accelerators
- CPU · NVIDIA CUDA · Apple Metal · AMD ROCm
- Model formats
- Safetensors · ONNX
- Source model
- Open source
- Licenses
- Apache License 2.0
- Boundary
- Represents the self-hosted Text Embeddings Inference server. Hugging Face Inference Endpoints, which can deploy this server on Hugging Face's managed infrastructure, is a separate service boundary. Text Generation Inference is Hugging Face's sibling runtime for causal language-model generation; its repository is archived and excluded from this collection, and this record does not stand in for it, since embedding, classification, and reranking are a distinct workload from generation.
Open in the directory → Open official documentation ↗ Repository ↗
Editorial ratings appear in the directory beside the profile they belong to and are never compared across collections.