paraphrase-multilingual-MiniLM-L12-v2 vs all-distilroberta-v1

Specs, VRAM requirements and download trends — updated 6 August 2026.

sentence-transformers · A
Params
120 M
Context
512
30d
59.4 M
apache-2.0 · commercial OK
sentence-transformers · B
Params
80 M
Context
512
30d
2.3 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification paraphrase-multilingual-MiniLM-L12-v2 all-distilroberta-v1
Parameters 120 M 80 M
Architecture BertModel RobertaForMaskedLM
Context length 512 512
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 50 1
Downloads 30d 59,393,322 2,318,073
Downloads all time 535.2 M 40.9 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2022-03-02

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

60.0 M2.3 M
paraphrase-multilingual-MiniLM-L12-v2 all-distilroberta-v1

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

all-distilroberta-v1 · fp16 0.9 GB / 24 GB
✅ Runs comfortably
paraphrase-multilingual-MiniLM-L12-v2 · fp16 1.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons