Sapling Logo

Gemma vs. Vicuna

LLM Comparison


Gemma

Gemma

Overview

Gemma is a family of lightweight open models from Google built using the same processes used for the the larger Gemini models.


Gemma was first released as a family of open models from Google -- 2B and 7B-parameter models, as of February 2024 -- intended for developers and compute-constrained devices. Despite their size, Gemma models compare favorably to other models of the same size such as the Mistral 7B model.


Initial release: 2024-02-21

Vicuna

Vicuna

Overview

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.



Initial release: 2023-03-30

Looking for an LLM API/SDK that works out of the box? No prompts or ad hoc guardrails.

Sapling API
More Comparisons

Gemma

Vicuna

Products & Features
Instruct Models
Coding Capability
Customization
Finetuning
Open Source
License Custom Noncommercial
Model Sizes 2B, 7B 13B