Sapling Logo

Gemma vs. Llama 3.1

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

Llama 3.1

Llama 3.1

Overview

Llama 3.1 added a 405B flagship model that was the first open-source model competitive with frontier proprietary models, alongside updated 8B and 70B variants with longer context and improved tool use.


Llama 3.1 was a landmark release for open-source AI. The 405B model achieved parity with GPT-4o and Claude 3.5 Sonnet on many benchmarks, marking the first time an open model reached the proprietary frontier. All models support a 128K token context window, multilingual generation in eight languages, and built-in tool-calling capabilities. The permissive license allows commercial use for most organisations, making Llama 3.1 a popular foundation for fine-tuning and self-hosted deployments.


Initial release: 2024-07-23

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

Sapling API
More Comparisons

Gemma

Llama 3.1

Products & Features
Instruct Models
Coding Capability
Customization
Finetuning
Open Source
License Custom Custom (Commercial OK)
Model Sizes 2B, 7B 8B, 70B, 405B