Running GLM-5.2 locally on a 256GB Mac with Unsloth

Melvin Vivas · X post · 2026-06-18 · Open on X

Topics: LLMOps, Deployment & Monitoring, LLM Fundamentals · Level: intermediate

Summary

Thanks to Unsloth's quantized builds, GLM-5.2 can now run locally on a Mac with 256GB of unified memory. The post gives a sense of the hardware needed to run large open-weights models yourself.

Key points

• Unsloth's quantized versions let GLM-5.2 run on a Mac with 256GB of unified memory.
• Even with quantization, running a frontier open-weights model locally needs very high-memory hardware.

Resources mentioned

• Unsloth · tool · unsloth.ai · free
  Open-source library for fast, memory-efficient fine-tuning of open LLMs (LoRA/QLoRA) on a single GPU or in Colab.
  Also in: Run Laya Decision models locally with Unsloth on 4GB RAM (Melvin Vivas on X · notes), Unsloth passes 500M model downloads on Hugging Face (Melvin Vivas on X · notes), Run Qwen-Image-2.1 locally on 12GB VRAM with Unsloth GGUFs (Melvin Vivas on X · notes), Base vs fine-tuned Gemma 4 E2B as a model router (Melvin Vivas on X · notes) and 29 more
• GLM 5.2 · tool · huggingface.co · free
  A GLM-family LLM (the transcript says 'GLM-5-2') that the demo ranked as a strong, affordable model for coding and design.
  Also in: Qwen3.8-Max on the Frontend Code Arena cost-performance frontier (Melvin Vivas on X · notes), Models That Work With the Hermes Agent for Personal Productivity (Melvin Vivas on X · notes), Open Model GLM 5.2 Helped Mitigate OpenAI-Caused Cyberattack (Melvin Vivas on X · notes), AI News Roundup: Claude Fable 5, Scientist AI, ZCode, NVIDIA RL (Melvin Vivas on X · notes) and 27 more