Qwen2.5-Coder-32B-Instruct-GPTQ-Int8
Qwen2.5-Coder-32B is an advanced open-source model for code generation and inference, supporting long texts and optimized for efficiency.
What is Qwen2.5-Coder-32B-Instruct-GPTQ-Int8?
Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 is a powerful code generation model with 32 billion parameters, optimized for coding tasks and long text processing. It excels in generating, inferring, and repairing code, supporting up to 128K tokens. Built on GPTQ 8-bit quantization, it offers high performance and efficiency while remaining open source for broad use and research.