BAAI · Embedding Models

BGE Large EN v1.5

Name: BGE Large EN v1.5
Author: BAAI

BAAI's English embedding model that ranked at the top of MTEB when released and remains a dependable default for retrieval.

Run it locally

With Ollama installed, download and start the default version with:

ollama run bge-large:335m

Variant	Download
bge-large:335m	671MB

Memory: About 671MB for the default bge-large:335m version (4-bit)
Formats: Safetensors (Hugging Face), GGUF (Ollama, llama.cpp, LM Studio)

The download size is roughly the memory (RAM or GPU VRAM) needed to load a variant; allow extra for long contexts. See our hardware guide.

Overview

The BGE (BAAI General Embedding) family from the Beijing Academy of Artificial Intelligence became one of the most used open embedding families.

Highlights

335M parameters
1024-dimensional embeddings
MIT license
Available in Ollama

Typical uses

English semantic search and RAG.

Things to consider

English only; 512-token inputs.
Download sizes refer to the default quantized versions in the Ollama library; full-precision weights are larger.

Specifications are taken from the model card on Hugging Face, the Ollama library and the provider’s announcement. Benchmark results depend on evaluation settings; see how AI benchmarks work.

#Embedding Models #Open Weights #Local AI #BAAI

Similar models

View all

Sentence TransformersAug 30, 2021

all-MiniLM-L6-v2

A tiny, fast sentence-embedding model from the Sentence Transformers project, still one of the most downloaded models for semantic search.

Type: Embedding
Context: 512
Weights: Open

BAAIJan 30, 2024

BGE-M3

Open multilingual embedding model from the Beijing Academy of AI supporting dense, sparse and multi-vector retrieval in over 100 languages.

Type: Embedding
Context: 8K
Weights: Open

BAAIMar 15, 2024

BGE Reranker v2 M3

A multilingual cross-encoder reranker from BAAI that reorders search results by relevance, a common second stage in RAG pipelines.

Type: Embedding
Context: 8K
Weights: Open