have you tried change "Base Font Size" in settings?
KomKross
Recent community posts
When I press rollback, for example, from page 8 to 5 and then continue my story, for example, to page 7, if I press rollback again, I am transferred to page 8 with the original story, which in theory should have been erased. I don't know how else to describe it, EN is not my first language, sry. You can see how it looks on the gif at the link below
https://drive.google.com/file/d/1WrdbeZ0qK4VzT3kRvgghoR0Ea11cu48E/view?usp=shari...
Glad to help, I also played around with hosting locally for a long time, but my weak PC can't even come close to the models that openrouter offers. Now you just need to find a model that suits your taste, configure promt for it and that's it. I tried mistralai/mistral-nemo and anthropic/claude-3.7-sonnet too but I didn't like them. You can also go to the "rankings" tab on the openrouter and filter the models by the roleplay tag and try some of them
I can say with 100% certainty that it is better to use free models via openrouter(there is guide on the main page) rather than running small models on your computer. To run smart and big models you need a high-end PC and small models, although they work, do not always do what you tell them and poorly follow the narrative
No matter what I try, there is nothing better than these three free models via Openrouter. "qwen/qwen3-235b-a22b:free" "deepseek/deepseek-chat:free" "microsoft/mai-ds-r1:free" Without censorship and restrictions, well, at least I didn’t notice. There is a guide on the main page with guide setup if anyone doesn't know.
On my opinion all the models you guys listed above are very small and simply cannot provide a well-developed answer and keep a long narrative. If you have extra money try this paid model" sao10k/l3.1-euryale-70b" or "x-ai/grok-3-mini-beta" He responds quickly, is more diverse and holds the narrative well.
On openrouter there is a daily limit on free models on one account, 50 requests or something. 10 bucks will upgrade your account and solve this problem by increasing it to 1000 requests per day, which is more than enough.