bert-base-NER vs CodonTransformer

Specs, VRAM requirements and download trends — updated 21 September 2026.

dslim · A

Params

110 M

Context

512

30d

1.4 M

mit · commercial OK

adibvafa · B

Params

90 M

Context

4,096

30d

270 K

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	bert-base-NER	CodonTransformer
Parameters	110 M	90 M
Architecture	BertForTokenClassification	BigBirdForMaskedLM
Context length	512	4,096
Licence	mit	apache-2.0
Commercial use	Allowed	Allowed
Languages	1	—
Downloads 30d	1,429,617	270,165
Downloads all time	97.0 M	2.2 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2022-03-02	2024-05-24

Daily snapshots, last 56 days (28 Jul – 21 Sep)

2.1 M270 K

bert-base-NER CodonTransformer

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

CodonTransformer · fp16 0.9 GB / 24 GB

✅ Runs comfortably

bert-base-NER · fp16 1.0 GB / 24 GB

✅ Runs comfortably