Inkling⬇16kTrending Model:#2
Ternary-Bonsai-27B-gguf⬇432kTrending Model:#3
Unlimited-OCR⬇2237kTrending Model:#4Bonsai-27B-gguf⬇1405kTrending Model:#5
GLM-5.2⬇545kTrending Model:#6
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF⬇63kTrending Model:#7
Qwythos-9B-Claude-Mythos-5-1M-GGUF⬇2133kTrending Model:#8
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive⬇1998kTrending Model:#9
krea2-identity-edit⬇0kTrending Model:#10
OvisOCR2⬇17kTrending Model:#1Inkling⬇16kTrending Model:#2Ternary-Bonsai-27B-gguf⬇432kTrending Model:#3Unlimited-OCR⬇2237kTrending Model:#4Bonsai-27B-gguf⬇1405kTrending Model:#5GLM-5.2⬇545kTrending Model:#6Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF⬇63kTrending Model:#7Qwythos-9B-Claude-Mythos-5-1M-GGUF⬇2133kTrending Model:#8Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive⬇1998kTrending Model:#9krea2-identity-edit⬇0kTrending Model:#10OvisOCR2⬇17k
Ornith-1.0-397B is a new open-source AI model built to help with agentic coding tasks. This release uses a reasoning process to break down problems before providing a final answer. It […]
LoopCoder-V2 is a new 7B code model that uses a Parallel Loop Transformer to scale test-time computation. This release applies shared transformer blocks repeatedly while keeping the parameter count fixed. […]
The Video Production Skill transforms an AI agent into a complete video creator. It handles everything from researching a topic and writing a script to generating voiceovers and rendering the […]
Laguna-M.1 is a large artificial intelligence model designed to help with coding tasks and long-term projects. It uses a specialized structure to activate only a portion of its parameters at […]
LFM2.5-Embedding-350M-GGUF is a new model designed to turn text into searchable data across 11 different languages. It works as a dense bi-encoder that creates a single vector for each document […]
North-Mini-Code-1.0-w4a16 is a new release that makes a large code generation model much smaller and easier to run on local hardware. It uses a compression technique to shrink the memory […]
The new release of Jaz brings a personal artificial intelligence system directly to your own machines. This open source platform lets you run various coding agents, schedule loops overnight, and […]
Noema-atlas is a new release that provides a peer-to-peer network for sharing local language model weight files directly between machines. The system downloads models from peers around the world while […]
Molmo-motion is a new vision-language model that forecasts 3D point trajectories based on natural-language action instructions. Given a short video history, some 2D query points, and an action description, it […]
Higgs_v3-TTS-ComfyUI is a new release that brings multilingual conversational text to speech into ComfyUI. It allows users to generate spoken audio in over 100 languages using a local AI model. […]
Mordant-12B-Think is a new AI model designed to generate detailed and narratively rich compositions for image generation. It uses chain-of-thought reasoning to analyze spatial relationships and construct deliberate meaning through […]
AudioX-Turbo is a new open source framework that generates audio and music from text, video, and existing audio signals. This release processes your inputs in just four steps to create […]
The newly released Dasheng-Audiogen is an open source artificial intelligence model that creates full audio scenes from text descriptions. Instead of producing just one type of sound, it can blend […]
Difforum is a set of custom nodes for ComfyUI that creates keyframe animations using math expressions, camera moves, and audio reactivity. It updates the classic Deforum workflow to work with […]
The new release of Huggingface-model-filter provides a powerful userscript to sort through Hugging Face models using positive and negative keywords. This tool displays a floating panel on your screen that […]
Texture2albedo-v2 is a new AI tool that extracts pure base color from textured images. It works by removing shadows, reflections, highlights, and specularity from original photos. This process leaves behind […]
The new release called one-node-flux-2-klein wraps the complete FLUX.2 [klein] workflow into a single user interface widget for ComfyUI. Users can access text to image generation, image editing, and painting […]
ComfyUI-Krea2T-Enhancer is a custom node designed to improve how closely Krea2 diffusion models follow text prompts. It works by adjusting the internal conditioning path during the sampling process without altering […]
Qwen-AgentWorld is a new language world model designed to simulate digital environments for AI agents. It predicts what happens next when an AI takes an action in text or visual […]
Qwythos-9B-Claude-Mythos-5-1M is a full-parameter reasoning model built on a deeply uncensored base. It processes up to one million tokens of text at once for massive code analysis and research. The […]