Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac

Alibaba's Qwen team has released the Qwen2.5-Coder Series, open-source language models for coding tasks. The 32B model claims to match GPT-4's coding abilities and performs well in various benchmarks. It can run on high-end consumer hardware like a 64GB MacBook Pro M2. Early tests show promising results, with the model generating functional code quickly. This release could significantly impact AI-assisted coding, offering a powerful local alternative to hosted models.