# Llama 3.3 70B requirements

Updated: 2026-06-15

llama family, 70B params, released 2024-12.

- Q4_K_M: 42.52 GB on disk; ~45.3 GB to run at 4k context
- Q8_0: 74.98 GB
- Context: 128k
- Run: `ollama run llama3.3:70b`
- Runs on 4 of 39 tracked devices

Sources: https://ollama.com/library/llama3.3, https://ollama.com/library/llama3.3/tags, https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF, https://lmarena.ai/leaderboard
More: https://localmodel.run/model/llama-3.3-70b