{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"LLM.co","title":"Build Your Private AI Server in the Right Order — Starting with the Workload","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/04309ed2\"></iframe>","width":"100%","height":180,"duration":328,"description":"Most private AI server projects fail before a model ever loads — because teams start with the GPU instead of the workload. This episode walks the correct build sequence, from defining your workload to sizing power and cooling.","thumbnail_url":"https://img.transistorcdn.com/Xh4c5SJy9DrgNKLAiE3osoWLXnIfy23Af9qWDM3xsOc/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8xZTc1/ZDRkMDY4NzRiMTU3/OTcyNTRmMDY5OTNi/NTcxMy5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}