Learn Glossary Blog Tools
AI Glossary

LLaMA (Large Language Model Meta AI)

Meta's family of open-weight large language models that brought frontier-level capabilities to the open-source community.

Versions

LLaMA 1 (2023): 7B-65B params, leaked and sparked open-source LLM revolution. LLaMA 2 (2023): 7B-70B, officially open with commercial license. LLaMA 3 (2024): 8B-405B, competitive with GPT-4.

Impact

LLaMA democratized access to high-quality language models. It spawned thousands of fine-tuned variants (Alpaca, Vicuna, CodeLlama) and proved that open models can approach proprietary model quality.

← Back to AI Glossary

Related Articles

Large Language Models

LLaMA: Meta's Open-Source LLM Revolution

 Large Language Models

Fine-Tuning LLMs with LoRA and QLoRA: A Practical Guide

 Large Language Models

LLM Quantization: Running Large Models on Small Hardware

 Large Language Models

LLM Tokenization: BPE, WordPiece, and SentencePiece

Related Concepts

Parameter (Model Weight) Quantization Adapter Fine-Tuning Fine-Tuning in AI FP16 / BF16 (Half Precision) Large Language Model (LLM) LoRA (Low-Rank Adaptation)
Last updated: March 5, 2026