---
title: "강문규 (@devsnack) | Hashnode"
description: "Nvidia dgx sparks gb10, Asus gx10, llm, local ai. Read the latest articles by 강문규 on Hashnode."
url: "https://hashnode.com/@devsnack"
---

@devsnack

# 강문규

@devsnack · Seoul, South Korea · Joined May 2026

Nvidia dgx sparks gb10, Asus gx10, llm, local ai

### [Qwen3.6 on DGX Spark: vLLM + NVFP4 + DFlash vs llama.cpp — 2x Faster at 88–104 tok/s](https://devsnack.hashnode.dev/qwen3-6-on-dgx-spark-vllm-nvfp4-dflash-vs-llama-cpp-2x-faster-at-88-104-tok-s?utm_source=hashnode&utm_medium=feed)

I benchmarked Qwen3.6-35B-A3B on DGX Spark GB10 using llama.cpp (45–50 tok/s) vs vLLM + NVFP4 + DFlash (88–104 tok/s). Full setup guide, docker-compose, troubleshooting, and real-world results.

10 min read · [devsnack.hashnode.dev](https://devsnack.hashnode.dev/qwen3-6-on-dgx-spark-vllm-nvfp4-dflash-vs-llama-cpp-2x-faster-at-88-104-tok-s?utm_source=hashnode&utm_medium=feed)

[May 6](https://hashnode.com/posts/qwen3-6-on-dgx-spark-vllm-nvfp4-dflash-vs-llama-cpp-2x-faster-at-88-104-tok-s/69fb2aa950ecad45331b9b3a)

### [Gemma 4 MTP Drafter on DGX Spark: 2.89x Speedup for Dense 31B — No Quality Loss](https://devsnack.hashnode.dev/gemma-4-mtp-drafter-on-dgx-spark-2-89x-speedup-for-dense-31b-no-quality-loss?utm_source=hashnode&utm_medium=feed)

An 870 MB drafter model turned Dense 31B from 6.5 → 18.8 tok/s. No model swap, no training, no quality degradation. If you have a DGX Spark, there's no reason not to use this. Key Results Model Fra

8 min read · [devsnack.hashnode.dev](https://devsnack.hashnode.dev/gemma-4-mtp-drafter-on-dgx-spark-2-89x-speedup-for-dense-31b-no-quality-loss?utm_source=hashnode&utm_medium=feed)

[May 6](https://hashnode.com/posts/gemma-4-mtp-drafter-on-dgx-spark-2-89x-speedup-for-dense-31b-no-quality-loss/69fb28d650ecad45331a34d9)

### [Every Optimized Model for NVIDIA DGX Spark GB10 — Benchmarked & Ranked (April 2026)](https://devsnack.hashnode.dev/optimized-models-nvidia-dgx-spark-gb10-ranked?utm_source=hashnode&utm_medium=feed)

Got your hands on an NVIDIA DGX Spark but have no idea which models to run on it? I scoured every GB10-optimized model on Hugging Face so you don't have to. Table of Contents What Makes DGX Spark Spe

8 min read · [devsnack.hashnode.dev](https://devsnack.hashnode.dev/optimized-models-nvidia-dgx-spark-gb10-ranked?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/optimized-models-nvidia-dgx-spark-gb10-ranked/69fb26b550ecad4533189683) [May 6](https://hashnode.com/posts/optimized-models-nvidia-dgx-spark-gb10-ranked/69fb26b550ecad4533189683)