Tag feed

Qwen3-VL image analysis using vLLM on DGX Spark

Mar 19 · 5 min read · I'm at the stage with my poster generation project where I am analysing poster images to create training data. It turns out that vLLM is an excellent inference engine for this use case due to its supp

SPSaiyam Pathakblog.kubesimplify.com

Here's What I Learned About Nemotron 3 Super -I Ran a 120B Parameter Model on Nvidia DGX Spark

Mar 14 · 15 min read · There’s a moment when you’re watching a model load into memory. The progress bar is filling up to 87 gigabytes and it hits you. You’re about to talk to something that has 120 billion parameters. Not t

TCThomas Cherickalthomascherickal.hashnode.dev

The Ultimate Guide to Run OpenClaw with 100% Security (Finally)

Mar 14 · 58 min read · This guide is for developers only. If you are not yet a Python and Git expert - please learn both before implementing the steps in this article! Python and Git expertise is necessary to run OpenClaw s

Setting up a local coding assistant on DGX Spark (4 months and still trying)

Feb 18 · 5 min read · Coding with a local AI was something I was looking forward to when I bought my DGX Spark. I work alongside an Agentic Engineering specialist, so I’m well aware of how this can accelerate coding (and slow it down, depending on what practices you adopt...

Alright then...adding vLLM to the mix

Feb 14 · 4 min read · A few months ago I started using my DGX Spark, and coming in with minimal experience of running local models, I wanted a simple and easy to understand inference engine (as I wrote in this article). Plus I could see the experts on the DGX Spark user g...

Running multimodal GLM4.6V Flash on DGX Spark

Feb 6 · 7 min read · I’m working on a poster generation project with a plan to train a model on typesetting layouts. To do this I am extracting example layouts from poster images using the multimodal model GLM4.6V Flash. It turns out this model is a little temperamental ...

BBBrian Baldockblog.brianbaldock.net

Learning Fine-Tuning on Nvidia DGX Spark - Part 2

Feb 3 · 4 min read · In Part 1 of this series, I got NVIDIA AI Workbench to accept a custom PyTorch base image on DGX Spark. Got the container validated, the GPU was visible, and CUDA worked. 🔗 Click here to read part 1 of this series By most checklists, the environm...

BBBrian Baldockblog.brianbaldock.net

Learning Fine-Tuning on Nvidia DGX Spark - Part 1

Jan 24 · 5 min read · If you are working with NVIDIA DGX Spark (or your own rig) and trying to do anything beyond toy experimentation, you will very quickly run into challenges. 👉 Setting up your own rig? See my previous article to get started Deploying Local AI Inferen...

Calling ComfyUI Programmatically on DGX Spark

Jan 13 · 6 min read · I recently resurrected a poster generation project I started a year ago. The idea is to create vintage-style poster backgrounds and then add the right font and layout for a given text and image. I paused that project because I wanted to use onboard m...

Updating GGUF Registry for new Llama Server UI

Jan 4 · 2 min read · No sooner had I build a GGUF model registry than llama.cpp released functionality to dynamically load and unload models from their new llama-server web UI! I had a play with this and realised that it doesn’t exactly work for my setup, mainly because ...