Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model.
Cost / License
- Free
- Open Source (Apache-2.0)
Platforms
- Mac
- Linux
- Windows

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model.

Built end-to-end by Tencent, Hy is a large language model engineered for excellence in content creation, reasoning, code, and conversation. From complex tasks in writing, research, and work, to everyday dialogue, knowledge, and creativity, Hy responds with precision, coherence...
