← All Models

Qwen3 0.6B

0.6B Min 1GB VRAM Full 2GB VRAM chatmultilingual

Ultra-lightweight Qwen3 for fast on-device chat on any hardware.

Run with Ollama

ollama run qwen3:0.6b

Which GPUs can run this?

Check my GPU →
📚 Learn to fine-tune Qwen3 0.6B — Pluralsight