GLM-5.2 model quantized for consumer hardware via Colibri engine

A quantized version of the GLM-5.2 model, named jlnsrk/GLM-5.2-colibri-int4, has been released on Hugging Face. This version is designed to run on consumer hardware by streaming experts from disk, requiring approximately 25 GB of RAM and 400 GB of fast local storage. The model uses a custom container format compatible only with the Colibri engine, not standard formats like GGUF or GPTQ. AI

IMPACT Enables running large models on consumer hardware by optimizing memory usage and leveraging disk streaming.

RANK_REASON Release of a quantized model variant with specific hardware requirements and a custom engine.

Read on Hugging Face Trending Models →

• Colibri
• GLM-5.2
• jlnsrk/GLM-5.2-colibri-int4
• zai-org/GLM-5.2-FP8

• model release
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →