Back to AIBriefs
LaunchAI Models

Z.ai releases open-weight GLM-5.2 with 1M context and IndexShare

Z.ai releases open-weight GLM-5.2 with 1M context and IndexShareHugging Face Blog

GLM-5.2 is a 753B parameter sparse MoE model (40B active) released under MIT license, matching Opus 4.8 on benchmarks like CritPt. It introduces IndexShare, reusing sparse-attention indexes every 4 layers for efficient 1M-token inference. Available on Hugging Face and via OpenRouter at $1.40/M input, $4.40/M output.

zai-org/GLM-5.22 days agozai-org
unsloth/GLM-5.2-GGUF1 day agounsloth
zai-org/GLM-5.2-FP81 day agozai-org
RT @mervenoyann: GLM-5.2 is comparable to Opus 4.8 🔥🥵 with 1M context > new IS attention reuses...2 days agoHugging Face
RT @victormustar: Open source MUST win 🔥 GLM-5.2 is free when used with Hugging Face Inference...12 hours agoHugging Face
RT @Zai_org: Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements...2 days agoAravind Srinivas
Video Friday: Atlas Versus a Fridge27 days agoEvan Ackerman
GLM-5.2 and IndexShare for Long-Context Sparse Attention14 hours agoSebastian Raschka
GLM-5.2 is probably the most powerful text-only open weights LLM1 day agoSimon Willison
[AINews] GLM-5.2: the top Frontend Coding model in the world, IndexShare for Speculative Decoding1 day ago
I can't believe this is real I have GLM 5.2 running 100% locally on my Mac Studio. 2 bit quant....5 hours agoAlex Finn
It's hard to pinpoint open-closed gap and so-on, but I trust the Arena team and just look where GLM...2 days agoNathan Lambert
Credit to GLM-5.2 Max, the new Chinese open weights model, for pulling this off. ...but you can see...2 days agoEthan Mollick
GLM 5.2 now available on AI Gateway2 days agoJerilyn Zheng
Jun 17, 9:01 AM
Z.ai releases open-weight GLM-5.2 with 1M context and IndexShare — AIBriefs