Qwen3 Coder 30B A3B
AffordableRun locallyEfficient 30B MoE coding model with only 3B active parameters.
Sparse activation delivers fast inference with strong coding performance. Good balance for self-hosted code assistance.
▼
Qwen3 Coder 30B A3B is somewhat expensive at $0.07/M tokens input and $0.27/M tokens output. The model supports a 160K context window.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Performance
Providers
Run locally
Run Qwen3 Coder 30B A3B on your own computer with the Local AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.
ollama pull qwen3-coder:30b-a3b-q4_K_M
Misc
Compare with
GPT 5.6 Solvs Qwen3 Coder 30B A3BGPT 5.6 Lunavs Qwen3 Coder 30B A3B
Claude Fable 5vs Qwen3 Coder 30B A3BClaude Opus 4.8vs Qwen3 Coder 30B A3BClaude Sonnet 5vs Qwen3 Coder 30B A3BClaude Haiku 4.5vs Qwen3 Coder 30B A3B
Gemini 3.6 Flashvs Qwen3 Coder 30B A3BGemini 3.5 Flashvs Qwen3 Coder 30B A3BGemini 3.5 Flash-Litevs Qwen3 Coder 30B A3BGemma 4 31Bvs Qwen3 Coder 30B A3B
Grok 4.5vs Qwen3 Coder 30B A3BGrok Build 0.1vs Qwen3 Coder 30B A3BGrok 4.1 Fastvs Qwen3 Coder 30B A3B
Muse Spark 1.1vs Qwen3 Coder 30B A3B
DeepSeek V4 Provs Qwen3 Coder 30B A3BDeepSeek V4 Flashvs Qwen3 Coder 30B A3B
MiniMax M3vs Qwen3 Coder 30B A3B
GLM 5.2vs Qwen3 Coder 30B A3B
Qwen3.7 Maxvs Qwen3 Coder 30B A3BQwen3.7 Plusvs Qwen3 Coder 30B A3BQwen3 Coder Nextvs Qwen3 Coder 30B A3B
Nemotron 3 Ultravs Qwen3 Coder 30B A3B
Mistral Small 4vs Qwen3 Coder 30B A3BFrequently Asked Questions about Qwen3 Coder 30B A3B▼
When was Qwen3 Coder 30B A3B released?
▼
Qwen3 Coder 30B A3B was released on July 31, 2025.
Who created Qwen3 Coder 30B A3B?
▼
Qwen3 Coder 30B A3B was created by Qwen.
How much does Qwen3 Coder 30B A3B cost?
▼
Qwen3 Coder 30B A3B costs $0.07/M input tokens and $0.27/M output tokens.
What is Qwen3 Coder 30B A3B API pricing?
▼
The Qwen3 Coder 30B A3B API is priced at $0.07 per million input tokens and $0.27 per million output tokens. You can access Qwen3 Coder 30B A3B through idapt.app alongside 200+ other AI models in one workspace.
Is Qwen3 Coder 30B A3B a reasoning model?
▼
No, Qwen3 Coder 30B A3B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Qwen3 Coder 30B A3B support image or vision input?
▼
No, Qwen3 Coder 30B A3B does not currently support image or vision input. It is a text-only model.
Does Qwen3 Coder 30B A3B support audio?
▼
No, Qwen3 Coder 30B A3B does not support audio input.
What is the context window of Qwen3 Coder 30B A3B?
▼
Qwen3 Coder 30B A3B has a context window of 160K tokens, meaning it can process approximately 120,000 words of context at once.
Is Qwen3 Coder 30B A3B open source?
▼
Qwen3 Coder 30B A3B is a proprietary model developed by Qwen. The model weights and training data are not publicly available.
Where can I use Qwen3 Coder 30B A3B?
▼
You can chat with Qwen3 Coder 30B A3B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Qwen3 Coder 30B A3B through Qwen's own API or platform.