Skip to content
TopicTracker
From HackerNewsView original
TranslationTranslation

GLM-5.2 – How to Run Locally

The page describes how to run the GLM-5.2 model locally using Unsloth, including setup steps, model loading, and inference instructions for both 4-bit and full precision modes on consumer hardware.

Background

- GLM-5.2 is a large language model (LLM) from the GLM family, developed by Zhipu AI (a Beijing-based AI company, formerly known as Tsinghua-UC Berkeley joint research group). It's one of China's leading foundation models, comparable to OpenAI's GPT series or Meta's Llama in scope.

Related stories

  • The author tests the new open-weights GLM 5.2 model against Gemini 3 Flash by having them play text adventure games within a fixed budget of $0.15 per attempt. A harness tracks achievements earned in each game to compare the models' performance.