Find what you need for your workflow.

Text modelQwen/Qwen2.5-1.5B-Instruct

Pegasus Mini

A small, on-device chat model distilled from Qwen2.5-1.5B-Instruct and shipped as a q4 GGUF so it runs offline in llama.cpp / Ollama / a phone shell / the browser (WebGPU). It is the offline brain of the hybrid...

Othergoogle/gemma-3-12b-it

DreamFast Gemma 3 12b It Heretic v2

An abliterated version of Google's Gemma 3 12B IT created using Heretic v1.2.0. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for video generation...

Toonout

our repository: our paper: ToonOut: Fine-tuned Background Removal for Anime Characters the dataset we collected to fine-tune this model Replicate endpoint to try out the model (courtesy of J. H. Cho @sprited)

OtherZhengPeng7/BiRefNet

Otherpnnbao-ump/VieNeu-TTS-v3-Turbo

VieNeu TTS v3 Turbo CPP

This repository contains the model asset package for running VieNeu-TTS v3 Turbo with the VieNeu-TTS.cpp C++ runtime.

Tower13 Girls - Ricolina

TOWER 13 GIRLS (PART 074)

TextualInversionSD 1.5

OtherFunAudioLLM/Fun-CosyVoice3-0.5B-2512

Cosy Norwegian

LoRA fine-tune of Fun-CosyVoice3-0.5B-2512 on Norwegian Bokmål speech. Trained as part of an internal self-hosted TTS stack.

OtherSebastianBodza/Kartoffel_Orpheus-3B_german_synthetic-v0.1

Furry Pixel

Hi everyone :D This is Furry Pixel Lora

Kartoffel Orpheus 3b German Synthetic GGUF

GGUF / ggml conversion of SebastianBodza/KartoffelOrpheus-3Bgermansynthetic-v0.1 for use with CrispStrobe/CrispASR.

Otherpkufool/keyword-spotting-models

Artist Style: Leonat

The artist style of Leonat

KWS Zipformer 3M CoreML INT8

Streaming, zero-shot, open-vocabulary keyword spotting for iOS / macOS / visionOS. Exported from icefall's KWS-finetuned Zipformer transducer (gigaspeech, 3.49M parameters) to CoreML with INT8 palettized weights,...

Otherallenai/SAGE-MM-Qwen2.5-VL-7B-SFT

SAGE MM Qwen2.5 VL 7B SFT GGUF

> The SAGE-MM-Qwen2.5-VL-7B-SFT from allenai is a 7B-parameter vision-language model fine-tuned from Qwen/Qwen2.5-VL-7B-Instruct, serving as the core decision-maker in the SAGE (Smart Any-Horizon Agent) system for...