turintech author hub
GLM 5.2 MaxMin108 GGUF Start here. Use the six IQ2 M fast shards 95.78 GiB on a 128 GB machine. MMLU is 61.84 versus 87.29 for the 2 bit parent; expect weaker world knowledge. Details how it was tested . < chart:start GLM 5.2 MaxMin108: MMLU accuracy % versus file size. Each poi…
Models
7
Downloads
1,756
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.