GLM-5.3 open-sourced with 1M context window, vLLM integration available
AccBalanced · x · 2026-08-29
Zai released the open weights for GLM-5.3, the most capable model in the GLM-5 series. It features a 743B-parameter MoE architecture (39B active), a 1M-token context window, and 128K max output. vLLM announced day-0 support, allowing deployment via vllm serve zai-org/GLM-5.3 -tp 8. The model defaults to native FP8 weights, fitting on a single node of 8xH200 or 8xH20, while maintaining compatibility with GLM-5.2 parsers and tool-calling paths.
Related event: Z.ai Open-Sources GLM-5.3, Touting Agentic Coding and Cyber Defense(9 posts)→
More from Models
- Unsloth releases GLM-5.3 GGUF version for local deployment — burny_tech · 2026-08-29
- GLM-5.3-Flash writes Blender script for automotive museum live — mishig25 · 2026-08-29
- Polymarket predicts 69% chance of Grok 5 release by year-end — Polymarket · 2026-08-29
- Community reacts to GLM-5.3 full weight release with 'My weights, my choice' — examachine · 2026-08-29
- GLM 5.3 Available in Perplexity Computer, Beats GLM 5.2 on WANDR Benchmark — perplexity_ai · 2026-08-29
- Dev Comparison: Kimi K3 Beats Claude 5.6 in Kernel Tasks, Codex Leads in Debugging — YouJiacheng · 2026-08-29