Z AI it released GLM-5.2, their latest flagship model for long-horizon tasks. According to the description, It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include:
- Solid 1M Context: A solid 1M-token context that stably sustains long-horizon work Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency
- Improved Architecture: they propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. They did also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20%
Pure Open: An MIT open-source license — no regional limits, technical access without borders
The Open Weights are available in here: https://huggingface.co/zai-org/GLM-5.2
Enjoy
Comments
0 contributions