BAAI / feature-extraction updated 2 years ago

bge-large-en-v1.5

If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3.

Params

340 M

Context

512

Downloads 30d

13.1 M

Likes

708

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

13.4 M12.9 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	1.3 GB	2.0 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: BertModel
Parameters: 340 M
Tensor type: F32
Context length: 512
Vocabulary: 30,522
Layers / heads: 24 / 16
Licence: mit
First seen on the Hub: 2023-09-12
Training datasets: undisclosed
MTEB ArguAna (reported): 77.027
MTEB BIOSSES (reported): 84.206737984757
MTEB ArxivClusteringP2P (reported): 48.56707792675
MTEB ArxivClusteringS2S (reported): 43.194533891824
MTEB BiorxivClusteringP2P (reported): 39.71453833765
MTEB BiorxivClusteringS2S (reported): 36.901083492844
MTEB AskUbuntuDupQuestions (reported): 77.823616057688
MTEB Banking77Classification (reported): 87.771893109649
MTEB CQADupstackAndroidRetrieval (reported): 32.795
MTEB AmazonPolarityClassification (reported): 92.394770195742
MTEB AmazonReviewsClassification (en) (reported): 47.807127928703
MTEB AmazonCounterfactualClassification (en) (reported): 69.693866480435
Added to our catalog: 2026-07-28

Compare with

bge-small-en-v1.5 72.4 M bge-base-en-v1.5 10.0 M Qwen3-Embedding-0.6B 9.8 M multilingual-e5-large 7.5 M mxbai-embed-large-v1 4.9 M all-MiniLM-L6-v2 2.9 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB