← All Models

Llama 3.2 3B

3B Min 2GB VRAM Full 6GB VRAM chatcoding

Llama 3.2 3B delivers solid instruction-following on budget hardware.

Run with Ollama

ollama run llama3.2:3b

Which GPUs can run this?

Check my GPU →
📚 Learn to fine-tune Llama 3.2 3B — Pluralsight