paraphrase-multilingual-mpnet-base-v2 vs Qwen3-VL-Embedding-2B
Specs, VRAM requirements and download trends — updated 6 August 2026.
sentence-transformers · A
Params
280 M
Context
512
30d
11.5 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | paraphrase-multilingual-mpnet-base-v2 | Qwen3-VL-Embedding-2B |
|---|---|---|
| Parameters | 280 M | 2.1 B |
| Architecture | XLMRobertaModel | Qwen3VLForConditionalGeneration |
| Context length | 512 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 50 | — |
| Downloads 30d | 11,516,808 | 1,350,626 |
| Downloads all time | 117.9 M | 8.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2026-01-07 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
11.6 M1.3 M
paraphrase-multilingual-mpnet-base-v2
Qwen3-VL-Embedding-2B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
paraphrase-multilingual-mpnet-base-v2 · fp16
1.8 GB / 24 GB
Qwen3-VL-Embedding-2B · fp16
5.5 GB / 24 GB
Adjacent comparisons
bge-m3 vs paraphrase-multilingual-mpnet-base-v2
paraphrase-multilingual-MiniLM-L12-v2 vs paraphrase-multilingual-mpnet-base-v2
all-MiniLM-L6-v2 vs paraphrase-multilingual-mpnet-base-v2
all-mpnet-base-v2 vs paraphrase-multilingual-mpnet-base-v2
nomic-embed-text-v1.5 vs paraphrase-multilingual-mpnet-base-v2
paraphrase-multilingual-mpnet-base-v2 vs multilingual-e5-base