Llama
FreeOpen model family from Meta for local and hosted LLMs.
Tool Info
Overview
Llama is a family of open models released by Meta, available in multiple sizes and capabilities.
Because the weights are available, teams can host and customize models in their own environments.
The ecosystem includes tools, adapters, and community projects for inference and fine-tuning.
It is a common base for local assistants, agents, and domain-specific models.
Features
- Open weights
- Multiple model sizes
- Fine-tuning support
- Community ecosystem
Pricing
Pros
- Fully open and free
- Self-hostable
- Large community
Best For
When NOT to Use
- Requires infrastructure to run
- No hosted service from Meta
Integrations & Models
Alternatives
Often Compared With
Tags
Related Guides
- Large Language Models
Learn how LLMs like GPT, Claude, and Llama process and generate human language at scale.
- Fine-tuning
Learn how to adapt a pre-trained model to your specific domain or task with custom training data.
- Generative AI
Understand how AI systems create new text, images, code, and more from learned patterns.
- LoRA
Low-Rank Adaptation - the most popular parameter-efficient fine-tuning method for adapting LLMs without full retraining.
- QLoRA
Quantized LoRA - fine-tune large models on consumer GPUs by combining 4-bit quantization with low-rank adapters.
- Llama
Meta Llama open-weight models - self-hosting, fine-tuning, quantization, and building on open foundations.
Stay Updated
Get the latest AI news, tools, and engineering guides delivered to your inbox.
Subscribe to Newsletter