meta-llama/llama

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

59579 stars · 9789 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Meta's official repository containing inference code and download scripts for Llama 2 large language models (7B to 70B parameters). The repo is now deprecated in favor of the consolidated Llama Stack repositories like llama-models and llama-toolchain.

Use cases

• run inference with llama 2 models locally
• download llama 2 model weights and tokenizer
• minimal example code to load llama models
• experiment with llama 2 7b and 70b checkpoints
• self-host llama 2 for research

When to choose

• you specifically need the original minimal Llama 2 inference reference code
• you want to study Meta's canonical example of loading and running Llama models

When to avoid

• you want actively maintained Llama tooling - use llama-models, llama-toolchain, or llama-cookbook instead
• you need fine-tuning, safety shields, or agentic features
• you want production inference serving - use vLLM, TGI, or Hugging Face transformers

Facets

library · maturity abandoned

llm-inference machine-learning deep-learning large-language-models artificial-intelligence deep-learning python llama meta model-weights deprecated transformers gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="meta-llama/llama")