AlphaFold 3 inference pipeline
High-Resolution Image Synthesis with Latent Diffusion Models
A Customizable Image-to-Video Model based on HunyuanVideo
Code for running inference and finetuning with SAM 3 model
Ling is a MoE LLM provided and open-sourced by InclusionAI
Wan2.1: Open and Advanced Large-Scale Video Generative Model
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
Phi-3.5 for Mac: Locally-run Vision and Language Models
Official inference repo for FLUX.1 models
Qwen3 is the large language model series developed by Qwen team
Official Python inference and LoRA trainer package
DeepSeek Coder: Let the Code Write Itself
ChatGLM-6B: An Open Bilingual Dialogue Language Model
Fast stable diffusion on CPU and AI PC
OCR expert VLM powered by Hunyuan's native multimodal architecture
A Powerful Native Multimodal Model for Image Generation
Achieving 3+ generation speedup on reasoning tasks
Inference script for Oasis 500M
Z80-μLM is a 2-bit quantized language model
Agentic, Reasoning, and Coding (ARC) foundation models
Code for running inference with the SAM 3D Body Model 3DB
Foundation Models for Time Series
Wan2.2: Open and Advanced Large-Scale Video Generative Model
RGBD video generation model conditioned on camera input
Qwen3-TTS is an open-source series of TTS models