惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Google DeepMind News
Google DeepMind News
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
酷 壳 – CoolShell
酷 壳 – CoolShell
WordPress大学
WordPress大学
小众软件
小众软件
博客园 - 司徒正美
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Jina AI
Jina AI
Hugging Face - Blog
Hugging Face - Blog
博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
量子位
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
雷峰网
雷峰网
云风的 BLOG
云风的 BLOG
M
MIT News - Artificial intelligence
F
Fortinet All Blogs
T
Tailwind CSS Blog
Martin Fowler
Martin Fowler
I
InfoQ
The GitHub Blog
The GitHub Blog
有赞技术团队
有赞技术团队
The Cloudflare Blog
罗磊的独立博客

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
[Day 1] DGX Spark Came Home — I Made It Draw a Cat
PEPPERCORN · 2026-05-04 · via DEV Community

[Day 1] DGX Spark Came Home — I Made It Draw a Cat

So... what is "local LLM" again?

Honestly, I'm still figuring out what "local LLM" even means. But somehow, through a series of decisions I won't fully justify here, I ended up buying an NVIDIA DGX Spark — and now it's sitting in my house.

DGX Spark: NVIDIA's "supercomputer for the home" — a small but seriously expensive box with the latest-gen AI chip inside. Apparently.

What I really want to figure out is: when should I use local AI vs. cloud AI? Reading articles about it doesn't seem to help, so I'm going full hands-on. Goal: 100 experiments, one per day-ish, until I have an evidence-based answer.

This is experiment#1.


First, the hardware

So this is what showed up at my door — solidly packed in a sturdy cardboard box.

DGX Spark box

When I opened it, I was surprised at how small it actually is. "This is the AI machine?" kind of small.

DGX Spark hardware (mesh sides)


Boot up → Initial OS setup

Power on, and an Ubuntu-based DGX OS 7.5.0 boots up.

Welcome screen

Get started screen

"Get started" — yes, please.

Language and timezone

Language and timezone

Standard Linux installer territory — same as Ubuntu?

Privacy settings

Privacy settings

Diagnostic data sharing prompts.

System update

Update started

The moment I plugged it in, it started updating itself. Modern Linux being Linux.

Setup complete

Setup complete

I picked a username and let the hostname auto-assign. DGX-side prep done.


Connecting from my Windows PC

Plugging a monitor into the DGX every time would be tedious, so I want to SSH in from my regular Windows machine (which I've nicknamed "myPC1").

NVIDIA provides a desktop app called NVIDIA Sync that's supposed to make SSH setup painless. So I install it.

NVIDIA Sync install

…and that's where I fell into a trap big-time. Windows OpenSSH refused to connect with a "your SSH config has weird permissions, can't trust it" error.

Full troubleshooting steps are in the collapsible "Tech details" section below.


Inside the DGX, finally

After much wrestling, I made it inside. Here's the rough lay of the land:

Item Spec
GPU NVIDIA GB10 Grace Blackwell
Memory 128GB (unified between CPU and GPU)
Storage 4TB SSD (basically empty)
CPU 20 cores (perf + efficiency combo)
Idle power 4W (yes, four)

128GB of memory is apparently 8–16x what's in a typical laptop.


Setting up image generation → 🐱

This is the main event. I'm setting up ComfyUI to generate the first cat from this DGX.

The ComfyUI interface looks like this:

ComfyUI connected

The "boxes connected by cables" view is intimidating at first, but the default workflow is pre-wired. You just type a prompt and hit Queue Prompt.

So:

a cute fluffy cat sitting on a sunny windowsill, photorealistic, high detail, beautiful lighting, soft fur, cinematic, masterpiece, best quality

A few seconds later...

ComfyUI cat 1

🐱 There it is — the very first cat my DGX has ever drawn!

Tweaked the prompt and made some more.

ComfyUI cat 2

Eyes a bit unsettling but yeah, fluffy cat.

ComfyUI cat 3

Going a touch dark there.

ComfyUI cat 4

…is this a cat? It feels artistic though.

ComfyUI cat 5

Distinctive composition.

Each masterpiece takes a few to a dozen seconds. That speed means I can iterate on prompts without thinking about cost — which turned out to be quite addictive.


Tech details (let the AI explain it)

The rest is the technical stuff. Read on if you're curious.

I'm a non-engineer poking at this stuff for the first time, so I had Claude (my AI pair programmer for this challenge) write up the technical details. Hopefully useful for anyone walking the same path.

  1. How to actually get SSH working on Windows

NVIDIA Sync should generate an SSH keypair, register the public key on the DGX side at ~/.ssh/authorized_keys, and let you connect without a password.

If it doesn't work, the cause is usually permissions on Windows SSH config files.

Symptom

$ ssh spark-XXXX.local
Bad permissions. Try removing permissions for user: [PC]\CodexSandboxUsers
on file C:/Users/[user]/.ssh/config.

Enter fullscreen mode Exit fullscreen mode

If you've installed Codex CLI or similar sandboxing tools in the past, the [PC]\CodexSandboxUsers group may have inherited permissions on ~/.ssh/.

Fix (run from an elevated PowerShell)

Use environment variables to avoid hard-coding your username/PC name.

# Take ownership
takeown /f "$env:USERPROFILE\.ssh\config"
icacls "$env:USERPROFILE\.ssh\config" /grant:r "$($env:USERNAME):F"

# Disable inheritance and remove the bad user
icacls "$env:USERPROFILE\.ssh\config" /inheritance:d
icacls "$env:USERPROFILE\.ssh\config" /remove "$env:COMPUTERNAME\CodexSandboxUsers"

Enter fullscreen mode Exit fullscreen mode

Use /inheritance:d rather than /inheritance:r:r strips all permissions, locking yourself out.

NVIDIA Sync's internal config files need the same treatment

~/.ssh/config Includes an NVIDIA Sync config file, and that one inherits the same problem.

$cfg = "$env:LOCALAPPDATA\NVIDIA Corporation\Sync\config\ssh_config"
icacls $cfg /inheritance:d
icacls $cfg /remove "$env:COMPUTERNAME\CodexSandboxUsers"

$key = "$env:LOCALAPPDATA\NVIDIA Corporation\Sync\config\nvsync.key"
icacls $key /inheritance:d
icacls $key /remove "$env:COMPUTERNAME\CodexSandboxUsers"

Enter fullscreen mode Exit fullscreen mode

Ghost SIDs that icacls can't remove

If you have SIDs from deleted user accounts lingering, icacls /remove won't touch them. You need PowerShell ACL manipulation:

$cfg = "$env:LOCALAPPDATA\NVIDIA Corporation\Sync\config\ssh_config"
$acl = Get-Acl $cfg
$badRules = $acl.Access | Where-Object {
    $_.IdentityReference.Value -like "S-1-5-*" -and
    $_.IdentityReference.Translate([System.Security.Principal.NTAccount]) -isnot [System.Security.Principal.NTAccount]
}
$badRules | ForEach-Object { $acl.RemoveAccessRule($_) | Out-Null }
Set-Acl -Path $cfg -AclObject $acl

Enter fullscreen mode Exit fullscreen mode

After this, ssh spark-XXXX.local connects on the first try (replace XXXX with your hostname).

  1. Commands to check DGX specs
# GPU
$ nvidia-smi
NVIDIA-SMI 580.142    Driver Version: 580.142    CUDA Version: 13.0
GPU 0: NVIDIA GB10    36C    P8    4W / N/A

# OS
$ uname -a
Linux spark-XXXX 6.17.0-1014-nvidia ... aarch64 GNU/Linux

# Memory
$ free -h
Mem: 121Gi  2.6Gi  118Gi

# Storage
$ df -h
/dev/nvme0n1p2  3.7T  47G  3.5T  2%  /

# CPU
$ lscpu
Architecture:  aarch64
CPU(s):        20
Model name:    Cortex-X925 + Cortex-A725

Enter fullscreen mode Exit fullscreen mode

Notable bits:

  • CUDA 13.0 (latest)
  • aarch64 (ARM64) architecture — yes, the DGX is ARM
  • 121Gi (≈128GB) unified memory
  • 20 cores in big.LITTLE layout (10 perf + 10 efficient)
  1. ComfyUI installation steps

Following the official NVIDIA Comfy UI playbook.

# Virtual environment
cd ~
python3 -m venv comfyui-env
source comfyui-env/bin/activate

# PyTorch with CUDA 13.0
pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu130

# ComfyUI itself
git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI
pip install -r requirements.txt

# Model (SD 1.5, ~2GB)
cd models/checkpoints/
wget https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/resolve/main/v1-5-pruned-emaonly-fp16.safetensors

# Launch server
cd ~/ComfyUI
python main.py --listen 0.0.0.0

Enter fullscreen mode Exit fullscreen mode

Key packages installed:

  • torch 2.11.0+cu130
  • cuDNN 9.19
  • NCCL 2.28
  • transformers 5.7.0
  • comfyui-frontend-package 1.42.15

Open http://spark-XXXX.local:8188 from your Windows PC's browser to access ComfyUI (XXXX is your hostname).

Download speed

The 2GB model came down at 40.6 MB/s in 50 seconds from HuggingFace's CDN. About half of my home 1Gbps LAN.


Tomorrow: Day 2

Day 2 plan: Train a LoRA on photos of my actual cat.

Today's SD 1.5 only knows "some cat from somewhere". With LoRA fine-tuning, I should be able to teach it about my specific cat. That kind of personalization feels like the killer feature of running locally.


100ExperimentsWithDGX #LocalLLM