Snowflake / sentence-similarity Open weights updated 1 year ago

snowflake-arctic-embed-m

Snowflake's Arctic-embed-m News Models Usage Evaluation Contact FAQ License Acknowledgement

Params

110 M

Context

512

Downloads 30d

371 K

Likes

167

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 69 days

▲ 28 K in the last 30 days (7.0%)

424 K371 K

Aug 17Sep 9Oct 2Oct 24

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: apache-2.0
First seen on the Hub: 2024-04-11
Training datasets: undisclosed
MTEB ArguAna (reported): 68.99
MTEB BIOSSES (reported): 86.747759739083
MTEB ArxivClusteringP2P (reported): 47.236254294113
MTEB ArxivClusteringS2S (reported): 37.433880471404
MTEB BigPatentClustering (reported): 19.116028913891
MTEB BiorxivClusteringP2P (reported): 36.96692185281
MTEB BiorxivClusteringS2S (reported): 31.980196985377
MTEB AskUbuntuDupQuestions (reported): 74.511607967287
MTEB Banking77Classification (reported): 79.649314224422
MTEB AmazonPolarityClassification (reported): 82.772048451102
MTEB AmazonReviewsClassification (en) (reported): 37.980133710535
MTEB AmazonCounterfactualClassification (en) (reported): 70.481984482221
Added to our catalog: 2026-08-17

Compare with any sentence-similarity model

Popular comparisons

all-MiniLM-L6-v2 193.4 M paraphrase-multilingual-MiniLM-L12-v2 40.6 M bge-m3 29.6 M all-mpnet-base-v2 17.9 M nomic-embed-text-v1.5 12.4 M multilingual-e5-small 9.2 M