Alibaba · 30B (3.3B active) · Mixture of Experts
Smaller MoE sibling to Qwen 3 Coder 480B — efficient agentic coding with 3.3B active
0 downloads
0 likes
2025-07 256K context
Use Cases
code
Mixture of Experts
Total experts: 128
Active experts: 8
Active params: 3.3B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| 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 | — |
GPUs that run Qwen 3 Coder 30B-A3B
Qwen 3 Coder 30B-A3B needs about 15.9 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 20 GB of VRAM or more (39 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 20 GB | RTX 4000 SFF Ada , RX 7900 XT , RTX 4000 Ada |
| 24 GB | RTX 4090 , RX 7900 XTX , RTX 3090 Ti |
| 32 GB | RTX 5090 , RTX 5000 Ada , Tesla V100 32GB |
About this model
Smaller MoE sibling to Qwen 3 Coder 480B — efficient agentic coding with 3.3B active