paraphrase-multilingual-MiniLM-L12-v2 vs embeddinggemma-300m
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 | embeddinggemma-300m |
|---|---|---|
| Parameters | 120 M | 300 M |
| Architecture | BertModel | Gemma3TextModel |
| Context length | 512 | — |
| Licence | apache-2.0 | gemma |
| Commercial use | Allowed | Conditional |
| Languages | 50 | — |
| Downloads 30d | 45,742,916 | 2,674,650 |
| Downloads all time | 608.7 M | 18.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2022-03-02 | 2025-07-17 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
60.0 M1.9 M
paraphrase-multilingual-MiniLM-L12-v2
embeddinggemma-300m
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
paraphrase-multilingual-MiniLM-L12-v2 · fp16
1.0 GB / 24 GB
embeddinggemma-300m · fp16
1.9 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