Alibaba · 0.6B · 密集（Dense）
Ultra-light Qwen 3 model for constrained devices 看看你的 GPU 或 Mac 跑不跑得動 Qwen 3 0.6B——最低 1 GB，建議 2 GB。
2025-0432K context
| 量化 | 位元 | VRAM | 品質 | 狀態 |
|---|---|---|---|---|
| Q4_K_M | 4 | 0.8 GB | good | — |
| Q6_K | 6 | 1 GB | excellent | — |
| Q8_0 | 8 | 1.1 GB | excellent | — |
Can I run Qwen 3 0.6B locally?
- Can I run Qwen 3 0.6B locally?
- Qwen 3 0.6B needs about 1 GB of memory at a minimum and 2 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Qwen 3 0.6B need?
- At Q4_K_M, Qwen 3 0.6B uses about 0.8 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.