S
S
Home / Models / BGE Large

BGE Large

by BAAI

9
KYI Score

High-quality embedding model for semantic search and retrieval.

LLMMITFREE335M
Official WebsiteHugging Face

Quick Facts

Model Size
335M
Context Length
N/A
Release Date
Sep 2023
License
MIT
Provider
BAAI
KYI Score
9/10

Best For

→Semantic search
→RAG
→Clustering
→Similarity

Performance Metrics

Speed

9/10

Quality

9/10

Cost Efficiency

10/10

Specifications

Parameters
335M
License
MIT
Pricing
free
Release Date
September 12, 2023
Category
llm

Key Features

Semantic searchHigh quality embeddingsMultilingualFast

Pros & Cons

Pros

  • ✓Excellent quality
  • ✓Fast
  • ✓MIT license
  • ✓Multilingual

Cons

  • !Embedding only
  • !Not generative

Ideal Use Cases

Semantic search

RAG

Clustering

Similarity

BGE Large FAQ

What is BGE Large best used for?

BGE Large excels at Semantic search, RAG, Clustering. Excellent quality, making it ideal for production applications requiring llm capabilities.

How does BGE Large compare to other models?

BGE Large has a KYI score of 9/10, with 335M parameters. It offers excellent quality and fast. Check our comparison pages for detailed benchmarks.

What are the system requirements for BGE Large?

BGE Large with 335M requires appropriate GPU memory. Smaller quantized versions can run on consumer hardware, while full precision models need enterprise GPUs. Context length is variable.

Is BGE Large free to use?

Yes, BGE Large is free and licensed under MIT. You can deploy it on your own infrastructure without usage fees or API costs, giving you full control over your AI deployment.

Related Models

LLaMA 3.1 405B

9.4/10

Meta's largest and most capable open-source language model with 405 billion parameters, offering state-of-the-art performance across reasoning, coding, and multilingual tasks.

llm405B

LLaMA 3.1 70B

9.1/10

A powerful 70B parameter model that balances performance and efficiency, ideal for production deployments requiring high-quality outputs.

llm70B

BGE M3

9.1/10

Multi-lingual, multi-functionality, multi-granularity embedding model.

llm568M