---
title: "Amegilla (@amegillaAI) | Hashnode"
description: "Building things, breaking them, trying again (and again). Read the latest articles by Amegilla on Hashnode."
url: "https://hashnode.com/@amegillaAI"
---

@amegillaAI

# Amegilla

@amegillaAI · London, United Kingdom · Joined November 2025

Building things, breaking them, trying again (and again)

### [Training a LoRA with Unsloth on DGX Spark](https://sparktastic.hashnode.dev/training-a-lora-with-unsloth-on-dgx-spark?utm_source=hashnode&utm_medium=feed)

Having done a long detour through manually reviewing and finessing my training data, this weekend I was finally ready to train the LoRAs for my poster generation project. I have two planned: One to g

13 min read · [sparktastic.hashnode.dev](https://sparktastic.hashnode.dev/training-a-lora-with-unsloth-on-dgx-spark?utm_source=hashnode&utm_medium=feed)

[Apr 5](https://hashnode.com/posts/training-a-lora-with-unsloth-on-dgx-spark/69d2749840c9cabf44f66dc4)

### [Qwen3-VL image analysis using vLLM on DGX Spark](https://sparktastic.hashnode.dev/qwen3-vl-image-analysis-using-vllm-on-dgx-spark?utm_source=hashnode&utm_medium=feed)

The benefits of parallel processing

5 min read · [sparktastic.hashnode.dev](https://sparktastic.hashnode.dev/qwen3-vl-image-analysis-using-vllm-on-dgx-spark?utm_source=hashnode&utm_medium=feed)

[Mar 19](https://hashnode.com/posts/qwen3-vl-image-analysis-using-vllm-on-dgx-spark/69bbd0ba8c55d6eefbce05bb)

### [Setting up a local coding assistant on DGX Spark (4 months and still trying)](https://sparktastic.hashnode.dev/setting-up-a-local-coding-assistant-on-dgx-spark-4-months-and-still-trying?utm_source=hashnode&utm_medium=feed)

Trying and failing to implement quality local AI code generation

5 min read · [sparktastic.hashnode.dev](https://sparktastic.hashnode.dev/setting-up-a-local-coding-assistant-on-dgx-spark-4-months-and-still-trying?utm_source=hashnode&utm_medium=feed)

[Feb 18](https://hashnode.com/posts/setting-up-a-local-coding-assistant-on-dgx-spark-4-months-and-still-trying/699640791474eba77a16b073)

### [Alright then...adding vLLM to the mix](https://sparktastic.hashnode.dev/alright-thenaddi?utm_source=hashnode&utm_medium=feed)

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...

4 min read · [sparktastic.hashnode.dev](https://sparktastic.hashnode.dev/alright-thenaddi?utm_source=hashnode&utm_medium=feed)

[Feb 14](https://hashnode.com/posts/alright-thenaddi/699071da245667f4ca3bbf71)

### [Running multimodal GLM4.6V Flash on DGX Spark](https://sparktastic.hashnode.dev/running-multimodal-glm46v-flash-on-dgx-spark?utm_source=hashnode&utm_medium=feed)

Tips & Tricks for invoking GLM4.6V Flash locally

7 min read · [sparktastic.hashnode.dev](https://sparktastic.hashnode.dev/running-multimodal-glm46v-flash-on-dgx-spark?utm_source=hashnode&utm_medium=feed)

[Feb 6](https://hashnode.com/posts/running-multimodal-glm46v-flash-on-dgx-spark/69864ea1ccd0712e734e15b6)