Llama
The best-known local model, now outdated. 8B runs on most laptops.
FreeOpen sourceRuns on your PC
- Best for
- Old guides and tutorials
- On your PC
- Some setup
- Works on
- Windows, Mac, Linux
- License
- Llama 3.1 Community
What’s good
- Runs on most laptops with 8 GB memory
- Supported by every app and tutorial
Downsides
- No new open Llama since April 2025
- Clearly behind Gemma 4 and Qwen at the same size
- Newer Llama 4 Scout is too big for most PCs
The details.
- Version
- Llama 3.1 8BReleased 2024-07
- Open source
- Yes, Llama 3.1 Community
- Made by
- Meta
- Website
- llama.com
Should you use it?
It is #10 of 10. Good for old guides and tutorials; for most people, Qwen is the better start.
Can I run it myself?
Yes. Some setup: download a model inside an app.
Use LM Studio, Ollama, Jan, llama.cpp.
- You need
- Any laptop with 8 GB RAM; faster with a graphics card
- Setup
- Some setupDownload a model inside an app
- Laptop, 8 GBRuns
- PC, 16 GB+Runs
- Mac, 16 GBRuns
- Mac, 32 GBRuns
- Mac, 64 GB+Runs
- PC, 8 GB GPURuns
- PC, 12 GB GPURuns
- PC, 16 GB GPURuns
- PC, 24 GB GPURuns
- WorkstationRuns