voyageai/voyage-4-nano
feature-extraction model by voyageai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
voyage-4-nano is a state-of-the-art text embedding model from the Voyage 4 series, designed for high-performance semantic search and retrieval tasks. This model features: For detailed performance metrics and benchmarks, please refer to: The shared embedding space introduced in the Voyage 4 model series eliminates the need to re-index your data when switching between models in the series. Embeddings generated by different Voyage 4 models (voyage-4-large, voyage-4, voyage-4-lite, and voyage-4-nano) can be directly compared and used interchangeably. For example, use voyage-4-large for high-fidelity indexing, voyage-4-lite for high-throughput queries, and voyage-4-nano for local development. Outperforms much larger existing embedding models, including voyage-3.5-lite. voyage-4-nano is trained with Matryoshka Representation Learning to enable flexible embedding dimensions with minimal loss of retreival quality. It supports 2048, 1024, 512, and 256 dimensional embeddings. voyage-4-nano uses quantization-aware training to enable flexible output data types with minimal loss of retreival quality. It supports 32-bit floating point, signed and…
Read the full model card ↗ · Preview checked 2026-10-31T14:34:21.180Z
Inside the original model card — Document outline
- voyage-4-nano
- Model Overview
- Key Features
- Shared Embedding Space with voyage-4 series
- Frontier Retrieval Quality at Low Cost
- Matryoshka Representation Learning (MRL)
- Quantization-Aware Training
- Usage
- Via Transformers
- Via Sentence Transformers
- Via vllm
- Via Ollama and llama.cpp (GGUF)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
voyageai/voyage-4-nano is a feature-extraction model repository published by voyageai on Hugging Face. The source reports the sentence-transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- feature-extraction
- Library
- sentence-transformers
- Recent downloads (30 days)
- 258,106
- Cumulative likes
- 148
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 346,451,968
- Architecture
- Qwen3ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-01-06T00:15:08.000Z
- Last modified
- 2026-10-22T18:59:41.000Z
Compatibility and lineage
Reported languages: multilingual
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:54:29.511Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.