# meta-llama/llama3

The official Meta Llama 3 GitHub site

Repository: https://github.com/meta-llama/llama3
Canonical: https://ross.abutalabs.com/products/llama3
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2025-01-26T21:39:06+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 3, release rhythm 35, longevity 64
- inputs: {"age_days": 901, "days_push": 584, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 29247, forks 3526 (observed 2026-08-28T04:11:53.216477+00:00)

## What it is
The official Meta repository for Llama 3, providing model weights download scripts, tokenizer, and minimal example code for running inference with 8B and 70B pre-trained and instruction-tuned language models. The repo is now deprecated in favor of the consolidated Llama Stack repositories such as llama-models and llama-toolchain.

## Use cases
- download llama 3 model weights
- run inference with llama 3 locally
- get llama 3 tokenizer example code
- experiment with open-source 8B and 70B language models
- fine-tune llama 3 starting code
- access meta llama models on hugging face

## When to choose
- you specifically need the original Llama 3 weights, download script, or reference inference code
- you want a minimal example of loading and running Llama 3 models

## When to avoid
- you are starting a new project - use the successor repos like meta-llama/llama-models or llama-toolchain instead
- you need fine-tuning recipes, agentic systems, or safety tooling, which moved to llama-cookbook, llama-agentic-system, and PurpleLlama
- you need a maintained inference library rather than example code

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, machine-learning, sdk
- domain: large-language-models, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: llama-3, model-weights, deprecated, meta, open-weights, tokenizer, gpu, linux

## Member repositories
- meta-llama/llama3 (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:53.216477+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 2026-08-29T16:53:08.472307+00:00, confidence not recorded.
  - readme: https://github.com/meta-llama/llama3 (fetched 2026-08-28T04:11:53.216477+00:00, sha 15630b4246b1)
- Data as of 2026-08-30T08:39:29.467469+00:00.