How deeply does Build Applications with Local AI Models on a Mac cover Gemma?

Compares release sizes and capabilities and gives an efficiency example, without detailing model internals.

Gemma

As explained in Build Applications with Local AI Models on a Mac

Gemma is a family of open language models developed by Google.

Gemma is a family of open-weight language models used when comparing models for practical applications. Its releases offer different sizes and capabilities, so choosing a Gemma model involves weighing factors such as quality, speed, and hardware demands. section 12.1.2 section 12.0

Notable releases show how the family has changed:

Gemma 1 (February 2024) came in 2B and 7B sizes; Gemma 2 (mid-2024) in 2B, 9B, and 27B. section 12.1.2
Gemma 3 (March 2025) added multimodal support, with sizes from 1B to 27B, a 128K context window, and support for over 140 languages. section 12.1.2
Gemma 4 (April 2026) is listed with an Apache 2.0 license, dense and MoE variants up to 31B, native vision and audio, and a 256K context window. section 12.1.2

Choosing a smaller model

A 9B Gemma 2 model can sometimes match or outperform larger models from other families. A small Gemma-family model is also used for quick local conversations on modest hardware. section 12.1.2

Model names and rankings change quickly. Check available models with `ollama list`, download one with `ollama pull <model>`, and check the Ollama library for current tags before choosing. section 12.0

How Build Applications with Local AI Models on a Mac covers it

Cover of Build Applications with Local AI Models on a Mac

liveBook manning.com

Read Build Applications with Local AI Models on a Mac on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Deep Learning with R, Third EditionGemma is a family of pretrained generative language models released in specialized instruction-tuned variants.
liveBook manning.com

Deep Learning with Python, Third EditionA pretrained large language model family used here for text generation and later instruction fine-tuning.

Compare how 3 books explain Gemma →

Related concepts

language modelkind of · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
KerasHubused by · KerasHub is a Keras library providing reusable components, pretrained models, and utilities for machine-learning and generative-modeling tasks.
Qwencontrasts with · Qwen is a family of pretrained generative language models developed by Alibaba Cloud, with variants for different tasks and modalities.
Ollamauses · Ollama is software for downloading, running, and serving language models locally.
open-weight modelkind of · An open-weight model is a machine-learning model whose trained parameter values are made available for others to download, run, or modify, subject to applicable terms.
model familykind of · A model family is a group of related models that share characteristics such as architecture, design, or training lineage.

This explainer was generated by Manning's knowledge graph from the text of Build Applications with Local AI Models on a Mac. The section links point to the parts of the book it draws on.