opt-125m vs distilgpt2
Specs, VRAM requirements and download trends — updated 20 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | opt-125m | distilgpt2 |
|---|---|---|
| Parameters | 125 M | 90 M |
| Architecture | OPTForCausalLM | GPT2LMHeadModel |
| Context length | 2,048 | — |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 7,387,919 | 2,092,198 |
| Downloads all time | 213.7 M | 256.2 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-05-11 | 2022-03-02 |
Download trend
Daily snapshots, last 55 days (28 Jul – 20 Sep)
18.6 M1.9 M
opt-125m
distilgpt2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
distilgpt2 · fp16
0.9 GB / 24 GB