OPT
Open Pre-trained Transformer Language Models (OPT) is part of the family of open source models designed to replicate GPT-3, with similar decoder-only architecture. It has since been superseded by models such as LLaMA, GPT-J, and Pythia.
A side-by-side comparison of release history, capabilities, licensing and model sizes.
| Attribute |
|
|
|---|---|---|
| Developer | Meta | Microsoft |
| Current generation | – | Phi-4 |
| Initial release | 2022-05-03 | 2023-06-20 |
| Instruct tuned | No | Yes |
| Coding | No | Yes |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | NA | MIT |
| Model sizes | 1.3B, 2.7B, 6.7B, 13B, 30B, 66B, 175B | 3.8B, 5.6B, 14B |
| Links |
Open Pre-trained Transformer Language Models (OPT) is part of the family of open source models designed to replicate GPT-3, with similar decoder-only architecture. It has since been superseded by models such as LLaMA, GPT-J, and Pythia.
Phi is Microsoft's family of compact open models designed for efficient local and edge deployment. Phi-4 is the current generation.
Microsoft introduced Phi-1 and Phi-2 to demonstrate how carefully curated and synthetic training data can make small models unusually capable. Phi-3 expanded the family for mobile and multimodal use. The Phi-4 generation includes a 14B general model and reasoning variants, plus smaller and multimodal checkpoints. Phi models are released under the MIT license and are designed for research, local inference, and resource-constrained production workloads.