NVIDIA releases quantized GLM-5.2 MoE model with 1M context

NVIDIA has released the GLM-5.2 NVFP4 model, a quantized version of ZAI's GLM-5.2. This Mixture-of-Experts model is optimized for reasoning and coding tasks, featuring sparse attention and a 1 million token context length. The model is ready for deployment in AI agent systems, chatbots, and RAG applications, and is available under the MIT License. AI

IMPACT This quantized MoE model with a 1M context window could accelerate deployment in AI agent systems and RAG applications.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Hugging Face Trending Models →

• GLM-5.2
• Hugging Face
• MIT License
• Nemotron-Competitive-Programming-v1
• Nemotron-Math-v2
• Nemotron-Science-v1
• Nemotron-SFT-Agentic-v2
• Nemotron-SFT-Instruction-Following-Chat-v2
• Nemotron-SFT-Multilingual-v1
• Nemotron-SFT-SWE-v2
• NVIDIA
• NVIDIA Blackwell
• nvidia/GLM-5.2-NVFP4
• SGLang
• vLLM

• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →