Model comparison
OPT-125M vs StarCoder2 15B
Capability radar, value bars, and side-by-side posture.
OPT-125M
Not scored
value score
StarCoder2 15B
70
value score
OPT-125M ctx
—
StarCoder2 15B ctx
16K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- StarCoder2 15B70
Attribute tape
| Field | OPT-125M | StarCoder2 15B |
|---|---|---|
| Developer | Hugging Face | Hugging Face |
| Context | — | 16K |
| Modalities | Text-generation | Text, Code |
| Openness | — | Open Weights |
| Speed | — | — |
| Price | — | — |
| Value score | — | 70 |
| Summary | OPT-125M is the smallest checkpoint in Meta AI's Open Pre-trained Transformer (OPT) family — a 125-million-parameter decoder-only language model released for open research use in text generation and fine-tuning tasks. It was among the first openly released GPT-3-class model families with full training details and weights shared publicly. | BigCode open coding model on Hugging Face. |