Aohan Zeng et al. at Tsinghua KEG and Zhipu AI published GLM-130B: An Open Bilingual Pre-trained Model, showing that a bidirectional autoregressive blank-infilling objective and DeepNorm stabilization scaled cleanly to 130B parameters with lossless INT4 weight quantization.
GLM (ChatGLM & GLM-4 / GLM-5)
Also known as: GLM · ChatGLM · GLM-4 · GLM-4.5 · GLM-5 · GLM-130B
Plain English
Zhipu AI and Tsinghua KEG's flagship family of open-weight and API language models—evolving from the early ChatGLM-6B local model into the large-scale GLM-4.5 and GLM-5 Mixture-of-Experts coding and reasoning models.
Technical Overview
Originally formulated around autoregressive blank infilling (GLM-130B, ChatGLM), the lineage transitioned to decoder-only Transformers with 2D/long-context RoPE in GLM-4, and to high-sparsity Mixture-of-Experts architectures with hybrid thinking/non-thinking modes and sparse attention in GLM-4.5 (355B/A32B) and GLM-5 (744B/A40B).
Timeline (5)
2022
Paper2023
ReleaseTsinghua and Zhipu AI released ChatGLM-6B, an open-weight 6.2B bilingual dialogue model runnable in 6 GB of VRAM via INT4 quantization that catalyzed early Chinese local LLM deployment and LoRA fine-tuning.
2024
PaperTeam GLM published ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools alongside open
GLM-4-9BandGLM-4V-9BCheckpoints, introducing native multi-step planning across web browsing, Python code execution, and function calling.2025
ReleaseZ.ai open-sourced GLM-4.5 (355B total / 32B active MoE) and GLM-4.5-Air (106B total / 12B active) under MIT, unifying chain-of-thought thinking and low-latency non-thinking modes for Claude Code and OpenCode harnesses.
2026
ReleaseZ.ai released GLM-5 under the MIT license, scaling the family to a 744B-parameter (40B active) MoE architecture with DeepSeek Sparse Attention (DSA) and asynchronous reinforcement learning (
slime) across 28.5T pretraining tokens.
See also (15)
Open full graphGLM (ChatGLM & GLM-4 / GLM-5)
10 more connections
- QwenOutgoing · Alternative to
- TransformerOutgoing · Implements
- CheckpointsOutgoing · Mentions
- Claude CodeOutgoing · Mentions
- Context Window & RoPEOutgoing · Mentions
- INT4Outgoing · Mentions
- LoRA & QLoRAOutgoing · Mentions
- OpenCodeOutgoing · Mentions
- Reasoning & Test-Time ComputeOutgoing · Mentions
- Tool Use & Function CallingOutgoing · Mentions