Text model

Voyage 4 nano

voyage-4-nano is a lightweight open-weight text embedding model from the Voyage 4 series. It features a 32,000-token context window, 340M total parameters, multilingual support, Matryoshka flexible dimensions (256 to 2048), quantization-aware training, and a shared embedding space compatible with all other Voyage 4 models. Licensed under Apache 2.0.

Type
Text
Weights
Open
Downloads
32k
Likes
144
Pipeline
feature extraction
License
apache-2.0

Model hub

voyageai/voyage-4-nano

Repo
voyageai/voyage-4-nano
Library
sentence-transformers
Access
Public
Technical tags and languages
sentence-transformers safetensors qwen3 text-generation transformers feature-extraction custom_code multilingual doi:10.57967/hf/9679 text-embeddings-inference endpoints_compatible
Open on Hugging Face

More from Voyage AI

12

About Voyage AI

1

Voyage AI provides best-in-class embedding models and rerankers for search and retrieval over unstructured data, used to power retrieval-augmented generation (RAG) and AI applications. It offers general-purpose, domain-specific (finance, legal, code) and company-specific fine-tuned models. Founded in 2023 and based in Palo Alto, the company was acquired by MongoDB, Inc. in February 2025 and now operates as a MongoDB subsidiary.