e5-large

e5-large is an E5-family embedding model for semantic search, multilingual retrieval, low-overhead indexing, or RAG pipelines.

Microsoft / intfloat · E5

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

Legacy large embedding baseline

Who should use it

Legacy large embedding baseline
Builders who want local or self-hosted testing options.
RAG builders comparing retrieval quality, latency, and multilingual coverage.

Common workflows

Legacy large embedding baseline
embedding workflows
rag workflows
semantic search workflows
retrieval workflows

Deployment and hardware notes

~1.34 GB in fp32 (335M parameters), ~0.67 GB in fp16; the serving footprint is exactly its v2 successor's.

License and usage notes

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

Strengths

Open weights where released model option for E5 workflows.
Legacy large embedding baseline
Existing indexes are not portable across versions: e5-large and e5-large-v2 vectors live in different spaces, so upgrading means re-embedding the corpus.

Limitations

Superseded by e5-large-v2 at identical size and dimensions — the v2 checkpoint ranks better on the same benchmarks, so new projects have little reason to start here.
~1.34 GB in fp32 (335M parameters), ~0.67 GB in fp16; the serving footprint is exactly its v2 successor's.
Context window and limits: 512 tokens.
Verify the exact model card, provider docs, license, and serving support before production use.

Local workflow notes

Existing indexes are not portable across versions: e5-large and e5-large-v2 vectors live in different spaces, so upgrading means re-embedding the corpus.

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

First-generation English E5 at 1024 dimensions with the same 'query: '/'passage: ' prefix contract as every E5. Kept for pipelines pinned to it; start new work on the v2 line.