Alibaba · 30B (3B active) · 専家混合（MoE）
Efficient agentic coding MoE — 3B active, 256K context 看看你的 GPU 或 Mac 跑不跑得動 Qwen 3 Coder 30B-A3B——最低 16.8 GB，建議 27.9 GB。
2025-07256K context
専家混合（MoE）
専家総数： 128
启用専家： 8
启用参数： 3.0B
| 量化 | 位元 | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| Q2_K | 2 | 10.1 GB | low | — |
| Q3_K_M | 3 | 13.9 GB | moderate | — |
| Q4_K_M | 4 | 15.9 GB | good | — |
| Q5_K_M | 5 | 19.7 GB | good | — |
| Q6_K | 6 | 23.6 GB | excellent | — |
| Q8_0 | 8 | 31.2 GB | excellent | — |
| F16 | 16 | 62 GB | lossless | — |
Can I run Qwen 3 Coder 30B-A3B locally?
- Can I run Qwen 3 Coder 30B-A3B locally?
- Qwen 3 Coder 30B-A3B needs about 16.8 GB of memory at a minimum and 27.9 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 Coder 30B-A3B need?
- At Q4_K_M, Qwen 3 Coder 30B-A3B uses about 15.9 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.