e5-base

e5-base 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 base embedding baseline

Who should use it

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

Common workflows

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

Deployment and hardware notes

~0.44 GB in fp32 — CPU-friendly, identical footprint to its v2 replacement.

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 base embedding baseline
The E5 prefix rule predates v2 and applies here too; embeddings are mean-pooled and compared by cosine similarity. At this size the whole index pipeline — embed, store, search — fits in a container with no GPU drivers installed.

Limitations

A first-generation checkpoint kept for compatibility; e5-base-v2 outranks it at the same 110M parameters and 768 dimensions. Benchmark deltas against v2 are largest on retrieval-heavy workloads, which is exactly where an embedder earns its keep.
~0.44 GB in fp32 — CPU-friendly, identical footprint to its v2 replacement.
Context window and limits: 512 tokens.
Verify the exact model card, provider docs, license, and serving support before production use.

Local workflow notes

The E5 prefix rule predates v2 and applies here too; embeddings are mean-pooled and compared by cosine similarity. At this size the whole index pipeline — embed, store, search — fits in a container with no GPU drivers installed.

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

Platforms: Windows, macOS, Linux

Embedding spec

Memory~0.44 GB in fp32 (110M parameters) · ~0.22 GB in fp16Output768-dimension vectorsMax input512 tokens

Only reach for it when reproducing results or maintaining an index built against it — v1 and v2 vectors are incompatible, and re-embedding into e5-base-v2 is the usual upgrade.