Meta Llama
The leading open-source large language model family
Meta Llama 3.1 is the most capable open-source LLM, available in 8B, 70B, and 405B parameter sizes. It runs locally or on any cloud, giving teams full control over their AI infrastructure with zero API costs.
Editor rating is our overall editorial judgment of the tool, out of 5. It is not a test score and not a user-review average. Ratings have not been re-scored since the tool was listed here. The reasons are in Best for and Pros & cons below.
Requires some technical comfort with API keys, command line, or coding. If you're new to AI, start with a chat-based tool first.
Best for
Pros & cons
✓ Pros
✗ What this won't do
Use cases
On-premise enterprise AI
Fine-tuned customer support bots
HIPAA-compliant medical AI
Offline AI applications
Install Ollama
Ollama is an app that runs AI models on your own computer. Download it from ollama.com and install it.
Run a small Llama
Open a terminal and run ollama run llama3.2. It downloads Meta's Llama 3.2 3B model, about 2 GB, and starts a chat.
Chat with it
Type a question at the prompt, and Llama answers in the terminal. Your own apps can also talk to it through Ollama's local API on port 11434.
Pick a size that fits
If your computer struggles, try the smaller ollama run llama3.2:1b. Llama 4, Meta's latest family, comes in much larger sizes that need a high-end computer.
Compare alternatives
| Tool | Category | Editor rating | Pricing |
|---|---|---|---|
| Meta Llama (current) | LLM / Assistant | 4.5 | Free (open-source) |
| Mistral AI | LLM / Assistant | 4.5 | Free (open) / API from $0.25/M tokens |
| ChatGPT | LLM / Assistant | 4.8 | Free / $20 mo |
| Claude | LLM / Assistant | 4.8 | Free / $20 mo |