>>
Run GLM-4.7 on Lium
Z.ai · Text generation · 358.3B parameters · 716.7 GB BF16 weights · released 2025-12-22
It needs about 861 GB of VRAM. The cheapest setup that runs it is 8x H200 (1128 GB), from $32.00 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-4.7:
vllm serve zai-org/GLM-4.7 --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does GLM-4.7 need?
About 716.7 GB for the released BF16 weights, so plan on 861 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-4.7?
8x H200 (1128 GB). On Lium that setup costs from $32.00 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt