pythia-160m vs gpt2-medium
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | pythia-160m | gpt2-medium |
|---|---|---|
| Parameters | 210 M | 380 M |
| Architecture | GPTNeoXForCausalLM | GPT2LMHeadModel |
| Context length | 2,048 | — |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 3,462,352 | 317,467 |
| Downloads all time | 26.3 M | 29.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-02-08 | 2022-03-02 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
3.5 M317 K
pythia-160m
gpt2-medium
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
pythia-160m · fp16
0.9 GB / 24 GB
gpt2-medium · fp16
2.2 GB / 24 GB