Gemma may be steadier than Qwen for daily Hermes agent use
worked better than as a daily model for in this firsthand setup. It followed complex saved rules more reliably. One memory rule said to use spoken output only when the user used , and to reply in the same language the user spoke.
Gemma followed that rule consistently, while Qwen sometimes used spoken output after typed input and mixed languages more often. Qwen still helped with some specific hard problems when switched in for those cases. For about 90% of the in this setup, Gemma handled the work well.
It also stayed strong at tool calls and coding, felt more natural in tone, and seemed better for more languages than Qwen, which felt more focused on English and Chinese.
Key points
- was more reliable as a daily model in this setup.
- Gemma followed a memory rule about voice replies and matching the user’s spoken language.
- sometimes used spoken output after typed input and mixed languages more often.
- Qwen still solved some harder specific problems when used separately.
- For multilingual and tool-heavy use, testing Gemma as the may be worthwhile.