← All Models

Llama 3.3 70B

70B Min 40GB VRAM Full 140GB VRAM chatcodingresearchreasoning

Meta Llama 3.3 70B — near-GPT-4 quality, best on dual 3090s or cloud GPU.

Run with Ollama

ollama run llama3.3:70b

Which GPUs can run this?

Check my GPU →
📚 Learn to fine-tune Llama 3.3 70B — Pluralsight