🎭 Fizz
MS3.2-24b-Angel
Base: Mistral Small 3.2-24B-Instruct-2506
A model finetuned for roleplaying, storywriting, and general instruct usecases. Strong prose and character portrayal rivaling 72B models.
Links:
Full |
EXL3 |
GGUF
|
Llama-3.3-70B Joyous
Base: meta-llama/Llama-3.3-70B-Instruct
Finetune designed for roleplay that also turned out to be comically good at assistant tasks.
Links:
Full
|
Luna-27B v0
Base: YanLabs/gemma-3-27b-it-abliterated-normpreserve-v1
Gemma 3 27B finetune intended for roleplay with unexpectedly excellent assistant capability (esp. media analysis / self-awareness).
Links:
Full
|
|
🎈 inflatebot
G2-9B-Blackout-R1
Base: google/gemma-2-9b
Task-arithmetic merge of Magnum-v3-9B with Sunfall. Great for character roleplay and story writing.
Links:
Full |
GGUF
|
MN-12B-Mag-Mell-R1
Base: Mistral-Nemo-Base-2407
Multi-stage merge of pre-trained Mistral Nemo models for roleplaying and writing.
Links:
Full |
EXL2 |
GGUF
|
|
🐦 Toasty Pigeon
Gemma-3-Glitter Series
Base: google/gemma-3-XXb-pt/it (4B/12B/27B)
A series of Gemma 3 based creative writing models in multiple sizes.
Links:
• 27B Full |
GGUF
• 12B Full |
GGUF
• 4B Full |
GGUF
|
Tlacuilo-12B
Base: LatitudeGames/Muse-12B (Mistral Nemo family)
Creative writing model tuned in stages (books → RP → small instruct) that holds up for RP/adventure.
Links:
Full
|
|
🌸 Auri/Aurorae
GLM-4-32B-0414 Neon v2
Base: THUDM/GLM-4-32B-0414
32B RP finetune with personality and variety. Feels nice, quirky, with good prose.
Links:
Full |
GGUF
|
GLM-4-9B-0414 Neon v2
Base: THUDM/GLM-4-9B-0414
9B RP finetune with personality and nice prose. Quirky but effective for RP.
Links:
Full |
GGUF
|
|
|