# Upgrade/Additions to properly run Local Models > Source: > Published: 2026-08-30 00:52:33+00:00 I had Codex help with trying to set up Qwen3.8-Flash on DeepSeek Harness on my main gaming PC. It was giving me some issues with memory and low context windows. What would be an inexpensive upgrade I could do to make this more feasible and would not cause issues on my PC when not running the local model? I currently can run Qwen3.8-27B-Q4 with a 50K context window. Is there a specific way I need to set up flash to run on my current specs? I know others with similar specs have got it working. My current PC specs are as follows CPU: Ryzen 7900X GPU: Radeon 7900XTX RAM: 96GB (2x 48GB) G-Skill Trident Z5 6400MHZ (usually 70-74GB of RAM is free at any time) Windows 11 (is there a way to compress its memory usage?) Thanks