Not sure this will help you but here is my answer:
For me it was mainly variations of models like DeepSeek and Qwen. Others I tried for languages (typically check the pronunciation of a word or a translation, to create a voice, etc). Unfortunately most of the time I used it my computer ended up shutting down unexpectedly because of the temperature of the motherboard so I gave up.
Only vanilla from Huggingface.
can't remember.
It has been now a year I have been waiting for an economic crisis hopping prices would drop to buy a GPU or a MacBook. So I have been mainly using models on Kagi in the meantime (Quick, Qwen, models used for translation, etc).
Not sure this will help you but here is my answer:
Unfortunately most of the time I used it my computer ended up shutting down unexpectedly because of the temperature of the motherboard so I gave up.
It has been now a year I have been waiting for an economic crisis hopping prices would drop to buy a GPU or a MacBook. So I have been mainly using models on Kagi in the meantime (Quick, Qwen, models used for translation, etc).