# Qwen 2.5 Coder 32B Instruct

> Canonical: https://www.overmindlab.ai/models/qwen-2-5-coder-32b-instruct

Dedicated Qwen 2.5 coder at 32B for code agents already on this family.

| Property | Value |
| --- | --- |
| Model ID | Qwen/Qwen2.5-Coder-32B-Instruct |
| Provider | Qwen |
| Group | Qwen 2.5 |
| Parameters | 32B |
| Tier | Large |
| Context window | 128K |
| Max training context | 32K |
| Tool calling | Yes |
| Training methods | — |
| Training cost | from $2.25 |
| Serving cost (per 1M output tokens) | from $20.00 |

## Overview

Qwen 2.5 Coder 32B Instruct is the dedicated coder in the mature Qwen 2.5 line. Keep it when your coding agent or eval harness is already tuned around Qwen 2.5 and you want controlled training rather than moving families.

The mature, heavily-benchmarked generation, including a dedicated coder model at 32B. Worth keeping when an existing pipeline is already tuned around it.

## Good for

- Code agents already on Qwen 2.5
- Tool-calling engineering workflows
- Stable baselines before a family upgrade

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

## Related models

- [Qwen 2.5 0.5B Instruct](https://www.overmindlab.ai/models/qwen-2-5-0-5b-instruct): 0.5B, 32K context
- [Qwen 2.5 7B Instruct](https://www.overmindlab.ai/models/qwen-2-5-7b-instruct): 7B, 128K context
- [Qwen 2.5 14B Instruct](https://www.overmindlab.ai/models/qwen-2-5-14b-instruct): 14B, 128K context
- [Qwen 2.5 72B Instruct](https://www.overmindlab.ai/models/qwen-2-5-72b-instruct): 72B, 128K context