# Qwen 2.5 32B / 72B Math + Code Mastery: GSM8K + MATH-500 + HumanEval FT Recipe

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-qwen-32b-72b-math-code-mastery
> Updated: 2026-05-14T14:42:52.845Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part IV — Mid-Large Models (13B-70B+) + Distributed Internals
**TLDR:** Qwen 2.5 32B/72B — math + code baseline beating Llama 70B. Math-heavy dataset mix (GSM8K + MATH + AIME + MetaMathQA), step-by-step CoT format, code execution loop, hyperparameter differences. 4×H100 80GB QLoRA 32B recipe (~3h).