gpt2 vs pythia-160m-deduped
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt2 | pythia-160m-deduped |
|---|---|---|
| Parameters | 140 M | 210 M |
| Architecture | GPT2LMHeadModel | GPTNeoXForCausalLM |
| Context length | — | 2,048 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 13,734,664 | 194,143 |
| Downloads all time | 901.9 M | 2.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2023-02-08 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
13.9 M162 K
gpt2
pythia-160m-deduped
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
pythia-160m-deduped · fp16
0.9 GB / 24 GB
gpt2 · fp16
1.1 GB / 24 GB