paraphrase-multilingual-MiniLM-L12-v2 vs sarashina-embedding-v1-1b
Specs, VRAM requirements and download trends — updated 21 September 2026.
sentence-transformers · A
Params
120 M
Context
512
30d
45.7 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | paraphrase-multilingual-MiniLM-L12-v2 | sarashina-embedding-v1-1b |
|---|---|---|
| Parameters | 120 M | 1.2 B |
| Architecture | BertModel | LlamaModel |
| Context length | 512 | 8,192 |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | 50 | 2 |
| Downloads 30d | 45,742,916 | 413,104 |
| Downloads all time | 608.7 M | 548 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2024-11-22 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
60.0 M408 K
paraphrase-multilingual-MiniLM-L12-v2
sarashina-embedding-v1-1b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
paraphrase-multilingual-MiniLM-L12-v2 · fp16
1.0 GB / 24 GB
sarashina-embedding-v1-1b · fp16
6.1 GB / 24 GB
Adjacent comparisons
all-MiniLM-L6-v2 vs paraphrase-multilingual-MiniLM-L12-v2
paraphrase-multilingual-MiniLM-L12-v2 vs bge-m3
paraphrase-multilingual-MiniLM-L12-v2 vs all-mpnet-base-v2
paraphrase-multilingual-MiniLM-L12-v2 vs nomic-embed-text-v1.5
paraphrase-multilingual-MiniLM-L12-v2 vs multilingual-e5-small
paraphrase-multilingual-MiniLM-L12-v2 vs paraphrase-multilingual-mpnet-base-v2