paraphrase-MiniLM-L3-v2
This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Params
20 M
Context
512
Downloads 30d
667 K
Likes
31
Download history
daily snapshots · 55 days
▲ 1.5 M in the last 30 days (69.8%)
2.1 M667 K
Aug 22Sep 1Sep 11Sep 20
2.6 M667 K
Jul 28Aug 15Sep 2Sep 20
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 | 0.1 GB | 0.6 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
- 20 M
- Tensor type
- F32
- Context length
- 512
- Vocabulary
- 30,522
- Layers / heads
- 3 / 12
- Licence
- apache-2.0
- First seen on the Hub
- 2022-03-02
- Training datasets
- flax-sentence-embeddings/stackexchange_xml, s2orc, ms_marco, wiki_atomic_edits, snli, multi_nli, embedding-data/altlex, embedding-data/simple-wiki, embedding-data/flickr30k-captions, embedding-data/coco_captions, embedding-data/sentence-compression, embedding-data/QQP, yahoo_answers_topics
- Added to our catalog
- 2026-07-28
Compare with any sentence-similarity model