>>
Run GLM-5.3 on Lium
Z.ai · Text generation · 753.3B parameters · 755.6 GB FP8 weights · released 2026-08-25
It needs about 907 GB of VRAM. The cheapest setup that runs it is 8x H200 (1128 GB), from $30.00 per hour, billed per second.
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve zai-org/GLM-5.3:
vllm serve zai-org/GLM-5.3 --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does GLM-5.3 need?
About 755.6 GB for the released FP8 weights, so plan on 907 GB with room for activations and KV cache at a short context. Longer contexts and bigger batches need more.
What GPU should I rent to run GLM-5.3?
8x H200 (1128 GB). On Lium that setup costs from $30.00 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt