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
source & further reading
forum.level1techs.com — original article
When Is It Worth Personally Preparing for AI Disasters?
What should the EA community be doing now that the (AIS) Overton window has opened up again?
Money Pumps for Agents Who Are Ambiguity Averse or Ambiguity Seeking