# shawwn/llama-dl

High-speed download of LLaMA, Facebook's 65B parameter GPT model

Repository: https://github.com/shawwn/llama-dl
Canonical: https://ross.abutalabs.com/products/llama-dl
Language: Shell
License: GPL-3.0
License Family: copyleft
Last push: 2023-06-28T16:56:55+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 91
- inputs: {"age_days": 1277, "days_push": 1162, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4114, forks 394 (observed 2026-08-28T04:08:35.790010+00:00)

## What it is
A shell script that provides high-speed curl-based downloads of Meta's LLaMA model weights (7B, 13B, 30B, 65B), fetching all weights in under two hours. It serves as a faster alternative to torrent-based distribution of the model files.

## Use cases
- download llama model weights fast
- curl llama weights instead of torrent
- download all llama 7b 13b 30b 65b checkpoints
- get llama weights on ubuntu server
- mirror facebook llama model files

## When to choose
- you want the original LLaMA weights quickly via curl rather than a torrent client
- you're on a Linux server and want a one-line download of all model sizes

## When to avoid
- you need Llama 2 or newer models
- you want inference or training code - this only downloads weights
- you're on macOS with the default bash, which lacks required array syntax support

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: llm-inference, cli, developer-tools
- domain: large-language-models, machine-learning, developer-tools
- platform: cli
- tags: llama, model-weights-download, shell-script, facebook-llama, linux, macos

## Member repositories
- shawwn/llama-dl (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:35.790010+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 2026-08-29T18:23:10.591440+00:00, confidence not recorded.
  - readme: https://github.com/shawwn/llama-dl (fetched 2026-08-28T04:08:35.790010+00:00, sha 326bb03a3fb0)
- Data as of 2026-08-30T08:39:29.467469+00:00.