Day 3 of my 100-experiment local LLM challenge. Threw 12 months of credit card data at Qwen 2.5 7B vs 72B on a DGX Spark. Takeaway: aggregate first with pandas, then let the LLM interpret.
Day 1 of my 100-experiment local LLM challenge with NVIDIA DGX Spark. Unboxing, setup, an SSH-permission rabbit hole, and finally — generating cats with ComfyUI.
![[Day 3] I Had a Local LLM Analyze a Year of My Credit Card Statements](https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fraw.githubusercontent.com%2FSAETAG%2Fdgx-100-experiments-images%2Fmain%2Fday03-credit-card-analysis%2F01-monthly-spending.png)
![[Day 1] DGX Spark Came Home — I Made It Draw a Cat](https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fraw.githubusercontent.com%2FSAETAG%2Fdgx-100-experiments-images%2Fmain%2Fday01-dgx-cat%2F10-cat-01.png)