bge-small-zh-v1.5
FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.
Params
20 M
Context
512
Downloads 30d
5.1 M
Likes
140
Download history
daily snapshots · 55 days
▲ 286 K in the last 30 days (6.0%)
5.1 M4.5 M
Aug 22Sep 1Sep 11Sep 20
5.1 M4.5 M
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
- 21,128
- Layers / heads
- 4 / 8
- Licence
- mit
- First seen on the Hub
- 2023-09-12
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any feature-extraction model