gpt2 vs gpt2-medium
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt2 | gpt2-medium |
|---|---|---|
| Parameters | 140 M | 380 M |
| Architecture | GPT2LMHeadModel | GPT2LMHeadModel |
| Context length | — | — |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 15,132,408 | 317,467 |
| Downloads all time | 926.2 M | 29.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2022-03-02 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
15.6 M317 K
gpt2
gpt2-medium
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt2 · fp16
1.1 GB / 24 GB
gpt2-medium · fp16
2.2 GB / 24 GB