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

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-qwen-32b-72b-math-code-mastery
> Updated: 2026-08-13T07:18:51.417Z
> 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'da Llama 70B'yi geçen baseline. Math-heavy dataset mix (GSM8K + MATH + AIME + MetaMathQA), step-by-step CoT format, code execution loop, hyperparameter farkları (lr daha düşük, ep daha çok). 4×H100 80GB QLoRA 32B reçetesi (~3 saat).