Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines
(3 edits) (+1)

Well the model I use is Cydonia-24B-v4.3-absolute-heresy.i1-Q4_K_M, is more in the NSFW side but so far it have been handling well enough and so far the bot doesn't go thirsty if I don't input any lewd stuff.

Speed wise: is more or less slow(1-3 words per second), sometimes go fast(maybe 4-6words per second) for some reason. but I dont mind the slowness.

Smartness wise it appears to handle decently when there are two or three characters (when using a CYOA char bot). I still need to check when using two bots in a group chat. Couple of times it got names the own model generated with the CYOA char bot.

And sure, though I suck in setting the min P and those type of parametes (I exported .json with those parameters already tweaked for Silly Tavern)


*But if it is a low priority it can wait :D

Cydonia-24B has been pretty good in my experience, though I did run into the same issue of it being a little slow, like you said. I will experiment with koboldcpp and add it in a future update if the quality is okay. Thanks!

hey if you need another tester for local Ilm, I got a 5060 to 16gb and so far I run 24 well in that area with fast speeds and even use an agent when I use marinara engine. I think the option of local would be awesome!

Hey ElPapaDon! I added local LLM support in v0.1.2. If you try it out, please let me know how it goes and what models work well

gotcha! ill give some feedback as i have today off so ill be touching upon this game alot xD