Qwen2.5-Coder-32B-Instruct is an LLM designed for advanced code generation, reasoning, and fixing. It excels in producing high-quality code across multiple programming languages, offering strong performance in code-related tasks while maintaining capabilities in mathematics and general knowledge.

Some other noteworthy features of Qwen2.5-Coder-32B-Instruct include support for long-context inputs and its foundation for code agent applications.

Metric	Value
Parameter Count	32.5 billion
Mixture of Experts	No
Context Length	131,072 tokens
Multilingual	Yes
Quantized*	No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.