GLM 5.3 SLIM GGUF
A GLM-5.3-class model that runs on a single NVIDIA B200, or on a Mac Studio with 192 GB or more of unified memory (with mlx-serve). At 179.9 GB it is 24.6% smaller than the 256-expert UD-IQ2M (238.6 GB), which does not fit in the memory of one B200 or a 192 GB Mac. On one B200 the whole model sits on the GPU and about 100K tokens of KV cache are left for up to 10 parallel requests; in our tests it scores 92.7% on HumanEval.
GLM 5.3 SLIM GGUF launched on 2 November 2026. It ranked #102 on Daily Launch on 10 November 2026 with a Launch Score of 21, from trending score 185 on Hugging Face. It moved down 25 places from the day before.
What is GLM 5.3 SLIM GGUF?
GLM 5.3 SLIM GGUF is a model by Scantist on Hugging Face. It is released under the glm-5.3 license.
How to get GLM 5.3 SLIM GGUF
pip install -U huggingface_hubFrom its model card on Hugging Face
More steps and the source are in its model card on Hugging Face.
Launch timeline
Launch Score, last 7 days
#173 of 228 in the roundup for the week of 9-15 November 2026.