1.3k likesNew · 8d old
563B GLM-5.3 model fits on a single B200 GPU
What is GLM-5.3-SLIM-GGUF?
GLM-5.3-SLIM is a 563-billion-parameter language model compressed to 180 GB, allowing it to run entirely on one NVIDIA B200 or a Mac Studio with 192 GB of unified memory. It scores 92.7 % on HumanEval while being 24 % smaller than the full-size version.
Who it is for
Developers who need a huge MoE model but lack a multi-GPU cluster can now experiment locally.
The story so far
Early Signal first spotted Scantist/GLM-5.3-SLIM-GGUF on November 8, 2026, with 1.3k likes. On its busiest day it gained 185 likes. The project is 8 days old. Early Signal files it under Inference, LLMs, RAG & Memory.
Questions about GLM-5.3-SLIM-GGUF
- What do I need to run GLM-5.3-SLIM-GGUF?
- NVIDIA B200 GPU or Mac Studio with ≥192 GB unified memory and mlx-serve installed