Llama Models — Hardware Requirements

19 Llama models from alpindale and the community, from the smallest that runs in 0.0 GB of VRAM up to 8.2B parameters. Every row links to full quantization tables and GPU compatibility.

All Llama Models by Size

ModelParamsContext
MicroLlama v245M2K
Llama 68M68M2K
Smol Llama 101M GQA101M1K
Llama 160M162M2K
MobileLLaMA 1.4B Chat1.4B2K
Llama Guard 3 1B1.5B131K
Llama 7B6.7B2K
Open Llama 7B7B2K
Llama Guard 3 8B8.0B—
Llama XLAM 2 8B Fc R8.0B131K
Meta Llama Guard 2 8B8.0B—
Llama Poro 2 8B Instruct8.0B8K
Llamatron 8B V18.0B131K
Llama Krikri 8B Instruct8.2B131K

Frequently Asked Questions

How much VRAM do I need to run a Llama model?
The smallest Llama model, Llama 68M, runs from 0.0 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which Llama models can I run on a 16 GB GPU?
12 of 14 Llama models fit in 16 GB of VRAM at some quantization, including Llama Guard 3 1B, Llama 68M, Llama 160M.
What is the most popular Llama model to run locally?
Llama Guard 3 1B is the most downloaded Llama model in local-friendly quantized formats. It runs from 0.8 GB of VRAM.