bert-base-NER vs distilbert-NER
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | bert-base-NER | distilbert-NER |
|---|---|---|
| Parameters | 110 M | 70 M |
| Architecture | BertForTokenClassification | DistilBertForTokenClassification |
| Context length | 512 | 512 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 1,273,360 | 237,094 |
| Downloads all time | 94.1 M | 2.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2024-01-25 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
1.4 M237 K
bert-base-NER
distilbert-NER
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
distilbert-NER · fp16
0.8 GB / 24 GB
bert-base-NER · fp16
1.0 GB / 24 GB