Qwen3 Coder 30B-A3B
Qwen3 Coder 30B-A3B is Alibaba's coding-specialized MoE (30B total, 3B active) under Apache-2.0, sitting at 7.4M Ollama pulls. It is the entry point into Alibaba's dedicated Qwen3-Coder line, whose smallest official variant starts at 30B.
Overview
Qwen3 Coder 30B-A3B is Alibaba's coding-specialized MoE (30B total, 3B active) under Apache-2.0, sitting at 7.4M Ollama pulls. It is the entry point into Alibaba's dedicated Qwen3-Coder line, whose smallest official variant starts at 30B.
Strengths
- Apache-2.0 license with commercial use allowed
- MoE (3B active) decodes fast relative to its 30B total size
- High adoption: 7.4M Ollama pulls for the coding-specialist line
Weaknesses
- No smaller official Qwen3-Coder variant exists below 30B
- Coding-specialized training — general chat quality not the design target
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 19.0 GB | 23 GB |
Get the model
Ollama
One-line install
ollama run qwen3-coder:30bRead our Ollama review →Hardware that runs this
Cards with enough VRAM for at least one quantization of Qwen3 Coder 30B-A3B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Qwen3 Coder 30B-A3B?
Can I use Qwen3 Coder 30B-A3B commercially?
What's the context length of Qwen3 Coder 30B-A3B?
How do I install Qwen3 Coder 30B-A3B with Ollama?
Source: Vendor official documentation
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Qwen3 Coder 30B-A3B runs on your specific hardware before committing money.