bge-large-en-v1.5

Large English BGE embedding checkpoint for passage retrieval and semantic search, with v1.5 tuned for more stable similarity scores.

BAAI · BGE

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedAugust 2026SourcesExact model card

Model checkpoints, context windows, provider support, local runtime compatibility, and license terms can change quickly. Verify the exact model card before production or commercial use.

Best for

English retrieval stacks that want a stronger embedding baseline for search and RAG before moving to multilingual models.

Who should use it

English retrieval stacks that want a stronger embedding baseline for search and RAG before moving to multilingual models.
Builders who want local or self-hosted testing options.
RAG builders comparing retrieval quality, latency, and multilingual coverage.

Common workflows

English embedding retrieval workflows
embedding workflows
rag workflows
retrieval workflows
semantic search workflows

Deployment and hardware notes

~1.34 GB in fp32 (about 0.67 GB in fp16) — any modern GPU holds it easily, and batch indexing is where the GPU pays off.

License and usage notes

MIT. Open weights. Verify the exact model card and license terms for the checkpoint or hosted provider you use.

Strengths

Open weights model option for BGE workflows.
English retrieval stacks that want a stronger embedding baseline for search and RAG before moving to multilingual models.
Short queries benefit from the 'Represent this sentence for searching relevant passages:' instruction; the v1.5 release made it optional rather than required.

Limitations

English only and 512 tokens per input; at 335M parameters query latency on CPU is noticeable, so plan for a GPU if traffic is interactive.
~1.34 GB in fp32 (about 0.67 GB in fp16) — any modern GPU holds it easily, and batch indexing is where the GPU pays off.
Context window and limits: 512 tokens.
Verify the exact model card, provider docs, license, and serving support before production use.

Local workflow notes

Short queries benefit from the 'Represent this sentence for searching relevant passages:' instruction; the v1.5 release made it optional rather than required.

Local runtimes: Ollama where supported, LM Studio where supported, llama.cpp where supported, Transformers

Platforms: Windows, macOS, Linux

Embedding spec

Memory~1.34 GB in fp32 (335M parameters) · ~0.67 GB in fp16Output1024-dimension vectorsMax input512 tokens

The strongest of the three English BGE v1.5 embedders, emitting 1024-dimension vectors. Choose it when ranking quality justifies a 2.7x larger index than bge-small and GPU-backed serving.