---
title: "#dgx-spark articles | Hashnode"
description: "Explore 4 articles tagged #dgx-spark on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/dgx-spark"
---

Tag

# #dgx-spark

4 posts · 0 followers

[DaShaun](https://hashnode.com/@dashaun) · [Sep 15](https://hashnode.com/posts/two-dgx-sparks-one-model-deepseek-v4-flash-with-a-1m-token-context/6aa97ecc9e408ed2c912ffef)

### [Two DGX Sparks, One Model: DeepSeek-V4-Flash with a 1M-Token Context](https://dashaun.hashnode.dev/two-dgx-sparks-one-model-deepseek-v4-flash-with-a-1m-token-context?utm_source=hashnode&utm_medium=feed)

Two NVIDIA DGX Sparks, one DeepSeek-V4-Flash model, and a full 1M-token context. The story behind the repo, the 30 MiB near-miss, and what I learned.

10 min read · [dashaun.hashnode.dev](https://dashaun.hashnode.dev/two-dgx-sparks-one-model-deepseek-v4-flash-with-a-1m-token-context?utm_source=hashnode&utm_medium=feed)

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

### [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)

[강문규](https://hashnode.com/@devsnack) · [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)

### [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)

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

### [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)
