# Qwen3 14B / 32B Base + YaRN: Long-Context FT (32K → 128K) RTX 4090'da Marjinal Mümkün

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-qwen3-14b-32b-yarn-long-context
> Updated: 2026-08-19T22:43:34.788Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part III — Small Open Models (1B–8B)
**TLDR:** Qwen3 14B'nin RTX 4090'da QLoRA + 32K context FT'si — mem peak 21 GB, marjinal sığıyor. YaRN rope-scaling math (β_fast, β_slow, scaling), long-context SFT dataset (NIAH + RULER), 32B'nin 4090'da imkansız olduğu yer. Cloud 1×H100 80GB alternatifi.