Get started
LLM Index

Phi vs. Vicuna

A side-by-side comparison of release history, capabilities, licensing and model sizes.

Attribute Phi Vicuna
Developer Microsoft UC Berkeley, CMU, Stanford, MBZUAI, UCSD
Current generation Phi-4 –
Initial release 2023-06-20 2023-03-30
Instruct tuned Yes Yes
Coding Yes No
Finetuning Yes Yes
Open source Yes Yes
License MIT Noncommercial
Model sizes 3.8B, 5.6B, 14B 13B
Links

Phi

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.

Further reading

Vicuna

Released alongside Koala, Vicuna is one of many descendants of the Meta LLaMA model trained on dialogue data collected from the ShareGPT website. According to the authors, Vicuna achieves more than 90% of ChatGPT's quality in user preference tests, while vastly outperforming Alpaca. As of May 2023, Vicuna seems to be the heir apparent of the instruct-finetuned LLaMA model family, though it is also restricted from commercial use.

Further reading

Compare other models

Other Phi comparisons

Other Vicuna comparisons