The RTX 5090 Loses To A Mini PC On Big AI Models
A hundred and twenty eight gigabyte mini PC, the GMKtec EVO-X2, holds an AI model an RTX 5090 can't even load. Chapters: 0:00 The EVO-X2 has no graphics card in it 2:23 AMD put 128 gigabytes in one pool 4:06 OpenAI gave away a 117 billion parameter model 5:18 gpt-oss-120b's own card asks for eighty gigabytes 6:31 Llama 70B answered at 2.7 tokens a second 8:05 Under 32 gigabytes the 5090 wins easily 9:29 Past the wall the 5090 borrows slow memory 11:17 Apple sells the bandwidth AMD and Nvidia don't 12:30 EXO Labs split it into prefill and decode 13:56 The EVO-X2 rose sixty percent in six months 15:31 gpt-oss-120b only wakes 5.1 billion parameters 17:13 So which one should you actually buy? About The Stack The Stack helps you build with AI. Each video takes one tool, model, or workflow and shows how it works in a few focused minutes, with the real benchmarks and real costs. We go deep on Claude Code and Cursor for AI coding, AI agents and MCP servers, the open-source AI tools and GitHub repos most people miss, RAG and vector search, fine-tuning, and running local LLMs on your own machine with Ollama and LM Studio. We compare models like ChatGPT and Claude, test AI automation with Zapier, Make, and n8n, and flag the tools that actually ship. Subscribe for new breakdowns: https://www.youtube.com/@the-stack-ai?sub_confirmation=1 #AI #BuildWithAI #ClaudeCode
