Model Anatomy See what's inside open-weight AI models

Can I run GLM-5.3-GGUF-DGX-Spark on an NVIDIA B200?

Yes, just

Its GLM-5.3-Q2-DGX-Spark file (161 GB) fits in the 162 GB an NVIDIA B200 can use, with room for ≈ 13K tokens of context.

Full analysis of GLM-5.3-GGUF-DGX-Spark Everything that runs on NVIDIA B200 Get the GLM-5.3-Q2-DGX-Spark file on Hugging Face
llama-server -hf autotrust/GLM-5.3-GGUF-DGX-Spark

Files and context on NVIDIA B200

Each file of GLM-5.3-GGUF-DGX-Spark (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn NVIDIA B200 Context (16-bit)Context (8-bit)
GLM-5.3-Q2-DGX-Spark161 GBTight13K27K

GLM-5.3-GGUF-DGX-Spark on other hardware

Popular models that run on NVIDIA B200

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.