LaBSE
Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained for sentence embedding for 109 languages. The pre-training process combines masked language modeling with translation language modeling. The model is useful for getting multilingual sentence embeddings and for bi-text retrieval.
Params
471 M
Context
512
Downloads 30d
550 K
Likes
54
Download history
tracking started — chart appears after 7 days of snapshots (2 recorded)550 K downloads in the last 30 days
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 | 1.9 GB | 2.6 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
- 471 M
- Tensor type
- F32
- Context length
- 512
- Vocabulary
- 501,153
- Layers / heads
- 12 / 12
- Licence
- apache-2.0
- First seen on the Hub
- 2022-03-02
- Training datasets
- CommonCrawl, Wikipedia
- Added to our catalog
- 2026-09-19
Compare with any sentence-similarity model