embedding

gte-multilingual-base

gte-multilingual-base is an Alibaba GTE text embedding model for multilingual retrieval with 8192-token input, dense and sparse outputs.

Alibaba (Qwen)China

Retrieval benchmark table comparing gte-multilingual-base with other embedding models.

Levelmodel

Classembedding

Parameters305M

Context8,192

Released20 Jul 2024

Opennessopen weights permissive

Runs onnot in the notes

Statusnot in the notes

R&D Topics

Retrieval-augmented generation (RAG)used by Text embeddings for semantic searchexemplar

Identity

Developer: Alibaba (Qwen)
Family: not in the notes
Released: 20 Jul 2024 sourcesregistry date
Weights published: 20 Jul 2024
Record checked: 11 Oct 2026

Where this comes from

Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture: other Encoder-only transformer; elastic dense embeddings (128 to 768) and sparse vectors
Total parameters: 305M sources
Active parameters: –
Checkpoint parameters: –
Context length: 8,192 tokens
Input: text
Output: not in the notes

Where this comes from

Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness: open weights permissive
Licence: Apache License 2.0 sources
Access routes: open weights download

Where this comes from

The licence file governs over registry tags and aggregator labels.

Deployment

Runs on: not in the notes
Footprint: not in the notes
Runtimes: not in the notes

Where this comes from

Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support: listed by developer
Regional languages: not in the notes
Jakarta hosting: unknown
Languages: Over 70 languages; card language tags include Indonesian

Where this comes from

Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Links

Developer

Alibaba (Qwen)big tech, China

Model

gte-multilingual-baseAlibaba (Qwen), embedding

R&D TopicsRetrieval-Augmented Generation (RAG)Text Embeddings for Semantic Search

Use CasesEmbeddings and Retrieval for SEA LanguagesPublic SectorUse cases of models in the same R&D topic; none is recorded for this model itself.

Who Runs Itnone recordedDeployments of these use cases; none names this model.

Graph

Organisations 1

Alibaba (Qwen)big tech, ChinaDeveloper

R&D topics 2

Retrieval-Augmented Generation (RAG)Grounding generation in retrieved documents.used by Text Embeddings for Semantic SearchTraining encoders that turn text in many languages into vectors so that search, clusterin…exemplar

Sources

huggingface.co/Alibaba-NLP/gte-multilingual-base https://huggingface.co/Alibaba-NLP/gte-multilingual-base
huggingface.co/api/models/Alibaba-NLP/gte-multilingual-base https://huggingface.co/api/models/Alibaba-NLP/gte-multilingual-base

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Gte-Multilingual-Base", https://aurion.semai.id/models/alibaba-gte-multilingual-base/, records of October 2026.