# Mixtral 8×7B / 8×22B FT: Router Collapse Problem + Aux Loss Weight Calibration

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-mixtral-fine-tuning-router-collapse
> Updated: 2026-05-14T14:42:53.297Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part V — MoE Internals & Fine-Tuning
**TLDR:** Most common Mixtral FT bug: **router collapse** — one expert dominates, others dead as training progresses. Capacity overflow, dynamic aux loss adaptation, expert balance metrics, FSDP + MoE compatibility (expert parallelism). Mixtral 8×7B QLoRA recipe on 4×H100 80GB (~4h).

