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

Traces major releases and strengths, but does not explain model internals or walk through a Llama-specific deployment.

Llama

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

A family of large language models developed by Meta.

Llama is a family of large language models from Meta. It is a practical starting point when choosing a model for general-purpose tasks, coding, reasoning, or instruction following. Meta released the original Llama in February 2023 as an open-weight model, meaning people could download and run it. section 12.1.1

The family has changed across releases:

Llama 1 began the family in early 2023; Llama 2 improved performance and had a more permissive license. section 12.1.1
Llama 3 and 3.1 brought further improvements in 2024, while Llama 3.2 added smaller, more efficient variants. section 12.1.1
Llama 4 arrived in April 2025 with Meta’s first mixture-of-experts architecture in the family and multimodal support. section 12.1.1

Choosing a local Llama model

In Ollama, run `ollama list` to see models already installed. Check the Ollama model library for current Llama tags, then use `ollama pull <model>` with the tag you choose. Compare candidates by size, speed, quality, and suitability for your task; model names and rankings change quickly. 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

LLMs in ProductionLLaMA is a family of autoregressive large language models released by Meta for research and development.
liveBook manning.com

Natural Language Processing in Action, Second EditionLlama 2 is a family of autoregressive large language models released by Meta for text generation and understanding.
liveBook manning.com

Starting Data Analytics with Generative AI and PythonA family of large language models developed by Meta for generative-AI applications.
liveBook manning.com

Software Testing with Generative AILlama-2 is an open-source family of large language models released by Meta that can be downloaded and further trained.

Compare how 5 books explain Llama →

Related concepts

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.
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.
open-source modelkind of · An open-source model is a machine-learning model whose relevant artifacts, such as code or weights, are made available under terms permitting public access and specified forms of use or modification.
Ollamaused by · Ollama is software for downloading, running, and serving language models locally.
weighthas part · A weight is a numerical quantity assigned to an element to represent its contribution, influence, importance, strength, or resource amount in a calculation or system.
api calluses · An API call is a programmatic request or invocation through an application programming interface to access data or invoke an operation.

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.