Z.ai ORG

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Open-source 6.2B-parameter Chinese-English chat model that runs on consumer GPUs through quantization, letting you self-host a ChatGPT-like assistant without cloud costs.

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Open-source AI phone agent that automates Android and iOS tasks by understanding screenshots and executing taps, swipes, and text input based on plain-language instructions.

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

ChatGLM2-6B is a free, open-source bilingual (Chinese and English) AI chat model with 6 billion parameters that runs on a single consumer GPU and can be fine-tuned on your own data.

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

ChatGLM3 is an open-source AI chat model that understands both Chinese and English, runs on consumer hardware, and supports tool calling, code execution, and long documents up to 128K tokens.

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Open-source AI models from Tsinghua University that generate short video clips from a text description or a starting image. The 2B model runs on older consumer GPUs and the 5B model fits on an RTX 3060.

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

CodeGeeX is a 13-billion-parameter AI model for code completion, generation, and translation across 20+ programming languages, available as a free VS Code and JetBrains plugin with no local GPU needed for the extension.

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

CodeGeeX2: A More Powerful Multilingual Code Generation Model

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

GLM-OCR: Accurate × Fast × Comprehensive

a state-of-the-art-level open visual language model | 多模态预训练模型

GLM-5: From Vibe Coding to Agentic Engineering

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

GLM-4-Voice | 端到端中英语音对话模型

CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.

GPT4V-level open-source multi-modal model based on Llama3-8B

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

An open-sourced end-to-end VLM-based GUI Agent

CogView4, CogView3-Plus and CogView3(ECCV 2024)

GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning

SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)

official code repo for paper "CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers"

GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters

Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

Official implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer

Official skills for the GLM family of models.

[AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

A real-time streaming conversational video system that transforms text interactions into continuous, high-fidelity video responses using autoregressive diffusion.

The official implementation of "Relay Diffusion: Unifying diffusion process across resolutions for image synthesis" [ICLR 2024 Spotlight]

No description.

Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

Complex Function Calling Benchmark.

GLM Series Edge Models

[ICCV 2025] LVBench: An Extreme Long Video Understanding Benchmark

Kaleido: Open-sourced multi-subject reference video generation model, enabling controllable, high-fidelity video synthesis from multiple image references.

The official Python SDK for Z.ai's large model open interface, making it easier for developers to call Z.ai's open APIs.

Z.ai Coding Plugins Marketplace in Claude Code

Official code for MotionBench (CVPR 2025)

No description.

official implementation of the paper "Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability".

Java SDK for Z.ai Open Platform

Self-hosted AI workspace with shareable AI teammates, shared conversations, memory, and governed access to plugins, MCP tools, and local devices.

No description.

GLM-SIMPLE-EVALS: The evaluation repository for the GLM-4.5 series of models by Z.ai.

No description.