# Llama 3.2 3B requirements

Updated: 2026-06-15

llama family, 3B params, released 2024-09.

- Q4_K_M: 2.02 GB on disk; ~3.2 GB to run at 4k context
- Q8_0: 3.42 GB
- Context: 128k
- Run: `ollama run llama3.2:3b`
- Runs on 39 of 39 tracked devices

Sources: https://ollama.com/library/llama3.2, https://ollama.com/library/llama3.2/tags, https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF, https://lmarena.ai/leaderboard
More: https://localmodel.run/model/llama-3.2-3b