# How to run NVIDIA Dory 4B with llama.cpp in a loop-by-loop guide

> Original title: How to Run NVIDIA Dory 4B with llama.cpp: Loop by Loop Guide

- Source: MarkTechPost
- Published: 2026-11-07T19:22:44.000Z
- Bad Influence: https://badinfluence.news/items/zttdlau64yklabutn5m8moejt
- Original: https://www.marktechpost.com/2026/11/07/coding-guide-nvidia-dory-4b-llama-cpp/

## Summary

MarkTechPost publishes a tutorial on running NVIDIA's Dory 1.0 4B reasoning model with llama.cpp, using the Dory branch pinned in NVIDIA's model card. The guide builds llama-server, downloads the 3.7 GB GGUF, and measures decode speed, cache memory, and GSM8K accuracy as the model's shared middle layers run one to four loops per token.