A practical model choice for Hermes Agent on weak PCs
can run locally on a low-end PC with an Intel i5-10400F, 16GB of memory, and a GTX 1650, but the may not help much and replies may be slow. The practical goal is to turn 800 pages of novel chapters into Markdown files, then ask about forgotten scenes, character descriptions, and other details across the draft.
Several models were tested for this kind of personal writing archive. did not work well, DeepSeek became unreliable in the first few messages, and Gemma made up too much information.
gave the steadiest results and had an acceptable reply speed. For weak hardware, it looks like a useful starting model when the job is searching and remembering long personal documents rather than getting instant answers.
Key points
- was tested locally on an Intel i5-10400F, 16GB of memory, and a GTX 1650.
- The main use was searching and remembering details from an 800-page novel draft saved as Markdown files.
- did not work well for this setup.
- DeepSeek became unreliable early, and Gemma made up too much information.
- was the most consistent model and responded at an acceptable speed.