gpt2 vs opt-125m

Specs, VRAM requirements and download trends — updated 20 September 2026.

openai-community · A
Params
140 M
Context
30d
15.4 M
mit · commercial OK
facebook · B
Params
125 M
Context
2,048
30d
7.4 M

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt2 opt-125m
Parameters 140 M 125 M
Architecture GPT2LMHeadModel OPTForCausalLM
Context length 2,048
Licence mit other
Commercial use Allowed Unknown
Languages 1 1
Downloads 30d 15,362,811 7,387,919
Downloads all time 925.8 M 213.7 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2022-05-11

Download trend

Daily snapshots, last 55 days (28 Jul – 20 Sep)

18.6 M7.4 M
gpt2 opt-125m A overtook B on 27 Aug

VRAM side by side

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

gpt2 · fp16 1.1 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons