Embeddings and rerankers · BAAI

BGE Reranker v2 M3

Hugging Face: BAAI/bge-reranker-v2-m3 · checked 2026-10-13

Multilingual cross-encoder reranker.

Datasheet

Maker	BAAI
Parameters	568 MVerifiedsafetensors.total from the HF API Source
Licence	Apache-2.0Verified
Access	Public download
Task (HF pipeline)	text-classification
First published on HF	2024-03-15
Last updated on HF	2024-06-24
Weights in memory	1.1 GB at 16-bit · 0.3 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build.

Benchmark

57.03

MTEB-R (reranking) · #2 of 2 scored in this category

MTEB-R, row in the Qwen3-Reranker card table (reranker metric). Source

See the full embeddings and rerankers ranking

The description summarises the model card at https://huggingface.co/BAAI/bge-reranker-v2-m3. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.