opt-125m vs pythia-160m-deduped
Specs, VRAM requirements and download trends — updated 10 November 2026.
EleutherAI · B · Open weights
Params
210 M
Context
2,048
30d
145 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | opt-125m | pythia-160m-deduped |
|---|---|---|
| Parameters | 125 M | 210 M |
| Architecture | OPTForCausalLM | GPTNeoXForCausalLM |
| Context length | 2,048 | 2,048 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 4,677,401 | 145,007 |
| Downloads all time | 222.9 M | 3.5 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-05-11 | 2023-02-08 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
17.5 M138 K
opt-125m
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