Qwen2.5 Coder 32B Instruct
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...
Specification
- Model ID
- qwen/qwen-2.5-coder-32b-instruct
- Weight license
- Apache-2.0 — open-weight; publisher source
- Modality
- Text >text
- Context
- 32.8K tokens
- Input
- $0.660/1M
- Output
- $1.00/1M
- Updated
- Nov 14, 2026
Scores
Capabilities
- No tool calling listed
- No vision support listed
- Standard context workflows
- Lighter reasoning profile
Input and output
Accepts Text inputs. Returns Text outputs.
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_ktop_p
Related models
Build with Qwen2.5 Coder 32B Instruct
Describe what you want to make and pick this model in the composer. A database and hosting are included.