sat-3l-sm vs wikineural-multilingual-ner
Specs, VRAM requirements and download trends — updated 10 November 2026.
Babelscape · B · Open weights
Params
180 M
Context
512
30d
649 K
cc-by-nc-sa-4.0 · non-commercial
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | sat-3l-sm | wikineural-multilingual-ner |
|---|---|---|
| Parameters | 210 M | 180 M |
| Architecture | SubwordXLMForTokenClassification | BertForTokenClassification |
| Context length | 514 | 512 |
| Licence | mit | cc-by-nc-sa-4.0 |
| Commercial use | Allowed | Not allowed |
| Languages | 85 | 10 |
| Downloads 30d | 459,768 | 649,452 |
| Downloads all time | 8.2 M | 18.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-06-16 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
693 K247 K
sat-3l-sm
wikineural-multilingual-ner
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
wikineural-multilingual-ner · fp16
1.3 GB / 24 GB
sat-3l-sm · fp16
1.5 GB / 24 GB
Adjacent comparisons
indonesian-roberta-base-posp-tagger vs wikineural-multilingual-ner
stanford-deidentifier-base vs wikineural-multilingual-ner
indonesian-roberta-base-posp-tagger vs sat-3l-sm
stanford-deidentifier-base vs sat-3l-sm
wikineural-multilingual-ner vs llmlingua-2-bert-base-multilingual-cased-meetingbank
wikineural-multilingual-ner vs ner-german-large