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 and GLM-5.3-Flash(28 posts)→
More from Models
- Nathan Lambert slams Meta's Muse Open License as 'trash' — natolambert · 2026-10-16
- Google launches Gemini 4 Argon to Ultra and Pro subscribers, touting physics and 3D skills — ShikharMurty · 2026-10-16
- Google gives X users early access to test Argon, not just companies — lyraxana · 2026-10-16
- Grok Voice 3.0 Tops Design Arena Speech Leaderboard, Up 7.4 Points — XFreeze · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- Meta open-sources Muse Spark: top US open model, scores just below DeepSeek — bindureddy · 2026-10-16