β All modelsMODEL FAMILY
Qwen 3 β every size compared
Alibaba's Qwen 3 family spans 7 models from 0.6B to 32.8B parameters. The smallest needs just 2 GB of RAM; the largest wants 32 GB.
All Qwen 3 models
| Model | Params | Download (Q4) | Min RAM | Context window | Best for |
|---|---|---|---|---|---|
| Qwen 3 0.6B | 0.6B | 0.4 GB | 2 GB | 32K | Chat |
| Qwen 3 1.7B | 1.7B | 1.0 GB | 3 GB | 32K | Chat |
| Qwen 3 4B | 4B | 2.4 GB | 6 GB | 32K | Chat, Reasoning |
| Qwen 3 8B | 8.2B | 5.0 GB | 8 GB | 128K | Chat, Reasoning |
| Qwen 3 14B | 14.8B | 9.0 GB | 16 GB | 128K | Chat, Reasoning |
| Qwen 3 30B-A3B | 30.5B (A3.3B) | 18.5 GB | 32 GB | 128K | Chat, Reasoning |
| Qwen 3 32B | 32.8B | 19.9 GB | 32 GB | 128K | Chat, Reasoning |
Sizes are 4-bit (Q4_K_M) GGUF builds β the standard for running models locally. Β· Data updated: 2026-06-11 Β· How we calculate these numbers β
Which Qwen 3 should you pick?
Take the largest one your memory allows β bigger versions of the same family are almost always better at the same quantization. Click any model for full requirements and a live check on your machine.