machine-learning on Machine Learning Stuffs

machine-learning on Machine Learning Stuffshttps://moisesvw.github.io/categories/machine-learning/Recent content in machine-learning on Machine Learning StuffsHugo -- gohugo.ioen-usSat, 05 Sep 2026 16:30:00 -0500Running Qwen3.8-27B on a 6 GB Laptop GPU (Slowly, but for Real)https://moisesvw.github.io/2026/september/qwen38-27b-on-6gb-laptop/Sat, 05 Sep 2026 16:30:00 -0500https://moisesvw.github.io/2026/september/qwen38-27b-on-6gb-laptop/This month my feeds filled up with posts about Qwen3.8-27B running at 50 to 75 tokens per second on an RTX 3090 with llama.cpp. Great numbers. My spare Linux laptop has an RTX 3060 Laptop GPU with 6 GB of VRAM, which is not even half of what the Q4 weights need. I wanted to know if the model could run on it at all. It can. As I write this, a coding agent on my LAN is talking to Qwen3.