zerofata/Q3.5-BlueStar-27B

27B • Updated 14 days ago • 105 • 35

Note Tested, but pretty much unusable outside of outputting low quality RP. Broken thinking, broken function calling. Way overtuned.

SicariusSicariiStuff/Impish_Magic_24B

24B • Updated Nov 10, 2025 • 11 • 45

Note Pretty generic Mistral 24B RP model. Not great, not bad. Just meh.

maldv/Loqwqtus2.5-32B-Instruct

Text Generation • 33B • Updated Mar 19, 2025 • 4 • • 2

Note Qwen3.2 -> fine-tune EVA -> fine-tune CoT model. Tested quickly, seems okay. ChatML + Think tags

LatitudeGames/Harbinger-24B

24B • Updated May 16, 2025 • 14 • 80

Note MS24B 3.1 (Base) fine-tune. ChatML. Trained on narrative at the second person *you do this*. Sounds good. Very versatile but sadly a bit too "dumb" to be featured on other listings.

google/gemma-3-27b-it

Image-Text-to-Text • 27B • Updated Mar 21, 2025 • 1.2M • • 1.92k

Note Meh. Extremely memory hungry at 16K context, unless you quant the KV cache which comes with its host of issues. It's to a point it's not worth testing for me (and neither are any finetunes by extension)

ACE-Step/Ace-Step1.5

Text-to-Audio • Updated Feb 3 • 33.1k • 645

Note Local Music Generation (untested)