EmbeddingCheck exact model cardOpen weights where releasedUpdated 2026

bge-small-en-v1.5

BAAI · BGE

bge-small-en-v1.5 is a BGE-family model for embeddings, reranking, retrieval, semantic search, or RAG workflows.

Best for

Lightweight local embedding workflows

Tradeoffs

Verify license, deployment requirements, runtime support, and fit on your own workload before production use.

Local hardware notes

Local hardware needs vary by size, quantization, and runtime. Check the exact model card and serving stack.

Local workflow notes

Use the exact checkpoint and quantization that matches your hardware and latency target.

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

Platforms: Windows, macOS, Linux

HardwareVaries by checkpointRuntimeOllama or LM Studio where supported, llama.cpp, Transformers, vLLMContextCheck official model cardLast updated2026
BAAI model page →

Related models

Qwen3 EmbeddingBuilders who want a newer embedding family to compare against E5, BGE, and Jina.BGE Reranker v2 M3RAG builders who need a practical reranker after Qdrant, Chroma, pgvector, or other vector search.Multilingual E5 LargeTeams building multilingual retrieval, semantic search, and RAG pipelines.