Sapling Logo

Gemma vs. Phi

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

Phi

Phi

Overview

Phi is a series of compact language models developed by Microsoft using high-quality synthetic data and curated web content. Phi-3 and Phi-3.5 (2024) significantly raised the bar for small models, with the 3.8B Phi-3 Mini matching much larger open-source models on key benchmarks.


Phi-1 and Phi-2 are 1.3B and 2.7B parameter language models, respectively, developed by Microsoft to demonstrate the ability of smaller language models trained on high-quality data. In April 2024, Phi-3 was released across Mini (3.8B), Small (7B), and Medium (14B) sizes. Phi-3 Mini achieves performance competitive with Llama 3 8B and Mistral 7B at a fraction of the compute, making it ideal for edge and constrained-resource deployments. Phi-3.5 Mini and MoE followed in August 2024 with further improvements.


Initial release: 2023-06-20

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

Sapling API
More Comparisons

Gemma

Phi

Products & Features
Instruct Models
Coding Capability
Customization
Finetuning
Open Source
License Custom MIT
Model Sizes 2B, 7B 1.3B, 2.7B, 3.8B, 7B, 14B