Find what you need for your workflow.

Darwin 28B KOREA I1 GGUF

For a convenient overview and download list, visit our model page for this model.

[COMMISSION] To Love-Ru - Nemesis

Commisions open, write me a PM on site(20$ character, can be discounted if order bunch of charas)

gemma-3-12b-it-Q8_0.gguf

[ILXL] Ayaka Sogou 十河綾香 | Hazurewaku no "Joutai Ijou Skill" de Saikyou ni Natta Ore ga Subete wo Juurin suru made ハズレ枠の【状態異常スキル】で最強になった俺がすべてを蹂躙するまで Failure Frame: I Became the Strongest and Annihilated Everything With Low-Level Spells - COMMISSION

Commissions are open if you have character wish to be made, please check my profile for details.

gummycandy_qwen.safetensors

Whisper Largev3 Myst Gclora

Whisper-large-v3 adapted to the MyST dataset with GC-LoRA (Gated Convolutional LoRA), from the paper "GC-LoRA: Gated Convolutional LoRA for Parameter-Efficient Acoustic Adaptation" (Interspeech 2026).

controlnetxlCNXL_sargeztT2iBinary.safetensors

Tap Dance City (umamusume)

LoHa of Tap Dance City (umamusume). Put LoHa file in your stable-diffusion-webui/models/ lora folder and write LoRA notation in prompt to applying LoHa. lora :yourlohaname:weight>

Snowshine スノーシャイン 昼雪 ( 明日方舟: 终末地 | Arknights: Endfield | アークナイツ:エンドフィールド )

blue eyes, short hair , grey hair , hair over one eye,hairclip,

Wan2.2-I2V-LowNoise-14B-Q4_K_S.gguf

Linny TokenBased Gen1.6 Large

Qwen2 0.5B GRPO Test

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct. It has been trained using TRL.

flux1-kontext-dev-fp8_e4m3fn.safetensors

Flux1-Schnell-Q8_0.gguf

Lacus Clyne ("GUNDAM seed" Serise) - Illustrious

Requested Character LoRA

Multiligual Arithmetic D64 L1 H2

This model is a fine-tuned version of []( on an unknown dataset.

Audio Optim

Its basically a Gemma4 E4B but optimized for audio and video analysis and image analysis on limited resources.

Gemma - Base+Summer Outfits [Monster Hunter Wilds]

Just a random fella doing random things in his spare time. Feel free to use the model or download it.