punctuate-all vs xlm-roberta-large-ner-hrl
Specs, VRAM requirements and download trends — updated 10 November 2026.
Davlan · B · Open weights
Params
560 M
Context
512
30d
246 K
afl-3.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | punctuate-all | xlm-roberta-large-ner-hrl |
|---|---|---|
| Parameters | — | 560 M |
| Architecture | XLMRobertaForTokenClassification | XLMRobertaForTokenClassification |
| Context length | 512 | 512 |
| Licence | mit | afl-3.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 569,752 | 245,704 |
| Downloads all time | 24.9 M | 3.3 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-04-09 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
822 K246 K
punctuate-all
xlm-roberta-large-ner-hrl
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
xlm-roberta-large-ner-hrl · fp16
3.0 GB / 24 GB