BAAI / feature-extraction Open weights updated 2 years ago

bge-base-en

Recommend switching to newest BAAI/bge-base-en-v1.5, which has more reasonable similarity distribution and same method of usage.

Params

110 M

Context

512

Downloads 30d

2.7 M

Likes

73

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

Download history

daily snapshots · 106 days

▲ 705 K in the last 30 days (35.6%)

2.7 M431 K

Jul 28Sep 1Oct 6Nov 10

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	0.4 GB	1.0 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: 110 M
Tensor type: F32
Context length: 512
Vocabulary: 30,522
Layers / heads: 12 / 12
Licence: mit
First seen on the Hub: 2023-08-05
Training datasets: undisclosed
MTEB ArguAna (reported): 73.684
MTEB BIOSSES (reported): 86.024851700868
MTEB ArxivClusteringP2P (reported): 48.88475477433
MTEB ArxivClusteringS2S (reported): 42.850531384032
MTEB BiorxivClusteringP2P (reported): 40.1754725088
MTEB BiorxivClusteringS2S (reported): 37.745141726873
MTEB AskUbuntuDupQuestions (reported): 74.648573187354
MTEB Banking77Classification (reported): 86.41301900942
MTEB CQADupstackAndroidRetrieval (reported): 32.096
MTEB AmazonPolarityClassification (reported): 92.548175126597
MTEB AmazonReviewsClassification (en) (reported): 46.285363943203
MTEB AmazonCounterfactualClassification (en) (reported): 69.817403611398
Added to our catalog: 2026-07-28

Compare with any feature-extraction model

Popular comparisons

bge-small-en-v1.5 47.6 M Qwen3-Embedding-0.6B 9.1 M bge-base-en-v1.5 8.3 M bge-large-en-v1.5 8.2 M granite-embedding-small-english-r2 6.9 M bge-base-en-v1.5 2.5 M