# meta-llama/llama-models

Utilities intended for use with Llama models.

Repository: https://github.com/meta-llama/llama-models
Canonical: https://ross.abutalabs.com/products/llama-models
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-02-11T16:38:31+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 40, longevity 56
- inputs: {"age_days": 797, "days_push": 203, "days_rel": 515, "gap_med": 21, "n_releases_24m": 4}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7685, forks 1408 (observed 2026-08-28T04:10:02.400794+00:00)

## What it is
Meta's official repository of Llama large language models with Python utilities for working with them, including model cards, licenses, and tokenizer support. It serves as the central hub for accessing Llama 2 through Llama 3.x model families and their associated tooling.

## Use cases
- download and run Llama models locally
- use the Llama tokenizer in my Python project
- find Llama model licenses and model cards
- build generative AI apps on top of Llama
- compare Llama model sizes and context lengths
- get started with open-weight LLMs from Meta

## When to choose
- you want official utilities, licenses, and model cards for Llama models
- you need the Llama tokenizer or model metadata in Python
- you're building on the Llama ecosystem and want the canonical source

## When to avoid
- you need a full inference server or serving framework
- you want fine-tuning tooling (see llama-cookbook instead)
- you need a permissively licensed library - the license is a custom Llama license

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, machine-learning, sdk, developer-tools
- domain: large-language-models, artificial-intelligence, deep-learning, developer-tools
- platform: python, cross-platform
- tags: llama, meta, model-weights, tokenizer, generative-ai, open-weights

## Member repositories
- meta-llama/llama-models (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.400794+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:36:01.915978+00:00, confidence not recorded.
  - readme: https://github.com/meta-llama/llama-models (fetched 2026-08-28T04:10:02.400794+00:00, sha 5c46e0cd6fb0)
  - registry_pypi: https://pypi.org/pypi/llama-models/json (fetched 2026-08-29T08:31:35.701621+00:00, sha 3e9b8023bfa6)
- Data as of 2026-08-30T08:39:29.467469+00:00.