BGE-M3

BAAI's multi-functionality + multilingual (170+ languages) + multi-granularity embedding. The default "just use it" RAG embedding since early 2024.

License: MIT · Context: 8192 tokens · Released: February 2024

The decision in five lines

The call: Consider — for docs
Best for: docs
Runs on: 23 hardware picks fit (cheapest: Intel Arc B580 12 GB · $249)
Watch out: English-only max-quality pipelines — `BAAI/bge-large-en-v1.5` or smaller English-tuned models beat BGE-M3 on English-only MTEB.
Evidence: Estimated · last verified April 2026

568M (XLM-RoBERTa-large base): PARAMETERS
EMBEDDING: TYPE
8192: CONTEXT
~1–2 GB: VRAM AT Q4

Where we recommend this

Every tier slot in the planner where this model is a top or alternate pick. Pulled live from planner.js — when the planner refreshes, this table stays current.

DOCS · MID

BGE-M3 (retrieval)Community-standard dense + sparse + multi-vector embeddings; multilingual; pairs with any generator.

The call

BAAI's multi-functionality + multilingual (170+ languages) + multi-granularity embedding. The default "just use it" RAG embedding since early 2024.
When not to use: English-only max-quality pipelines — `BAAI/bge-large-en-v1.5` or smaller English-tuned models beat BGE-M3 on English-only MTEB. BGE-M3's edge is breadth.

Runner notes

Ollama tag `bge-m3`. Also natively in FlagEmbedding, sentence-transformers, llama.cpp. 568M params run fine on CPU for small corpora.

License: MIT
Released: February 2024
Maker: BAAI
Model card: huggingface.co/BAAI/bge-m3 →

Hardware that fits

Every hardware pick whose memory fits this model at the quant we recommend. Sorted cheapest-first — the top row is your best-value fit. Click through for the full buyer’s guide.

Next step

Find-by-model — see what hardware runs this→