*I get asked almost daily about how to host custom SLMs in production. Here's my advice for anyone looking to get hands on experience without breaking the bank:

We all know you have a gaming PC, and if you don't I got one for $500. Target 6+GB of VRAM on the GPU.

Find open source models on Hugging Face. For 6GB of VRAM I would recommend Qwen3-1.7B (https://lnkd.in/gzy4cpyR) or gemma-3-1b (https:…*