# Qwen 3 Coder 30B MoE

> Canonical: https://www.overmindlab.ai/models/qwen-3-coder-30b-a3b-instruct

Code-specialised Qwen 3 MoE with 256K context and tool calling.

| Property | Value |
| --- | --- |
| Model ID | Qwen/Qwen3-Coder-30B-A3B-Instruct |
| Provider | Qwen |
| Group | Qwen 3 |
| Parameters | 30B MoE (3B active) |
| Tier | Mid |
| Context window | 256K |
| Max training context | 256K |
| Tool calling | Yes |
| Training methods | — |
| Training cost | from $2.00 |
| Serving cost (per 1M output tokens) | from $8.00 |

## Overview

Qwen 3 Coder 30B is the code-specialised mixture-of-experts model in the Qwen 3 family: 30B total weights with 3B active per token, with a full 256K context for both inference and training. Train it on your agent's coding traces, then benchmark it against the model you run in production today.

The widest size ladder in the catalogue, 0.6B through 32B, plus a code-specialised mixture-of-experts model. Useful when you want to hold the family constant and vary only size across parallel experiments.

## Good for

- Code generation and repair agents
- Tool-calling engineering loops
- MoE serve cost with a code-oriented base

Train this model on your agent's data: https://docs.overmindlab.ai/models/training.md

## Related models

- [Qwen 3 4B](https://www.overmindlab.ai/models/qwen-3-4b): 4B, 128K context
- [Qwen 3 1.7B](https://www.overmindlab.ai/models/qwen-3-1-7b): 1.7B, 128K context
- [Qwen 3 0.6B](https://www.overmindlab.ai/models/qwen-3-0-6b): 0.6B, 128K context
- [Qwen 3 8B](https://www.overmindlab.ai/models/qwen-3-8b): 8B, 128K context