LLM
How to deploy GLM-4.6 on a GPU cloud
A 357B (MoE) language model for chat and instruction-following. Full specs, license and use cases.
GLM-4.6 size and hardware requirements
356.8B
Total parameters
Mixture-of-experts: 8 of 160 experts active per token (exact active-parameter count not stated on the model card)
Active parameters
BF16
Published precision
797.5 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 664.6 GB | 797.5 GB | No capable live offer found | – | – |
| FP8 (quantized) | 332.3 GB | 398.7 GB | RTX PRO 6000 | 5 | $8.20/hr |
| INT4 (quantized) | 166.1 GB | 199.4 GB | RTX A6000 | 5 | $1.65/hr |
How to run GLM-4.6
Run GLM-4.6 with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve zai-org/GLM-4.6 --tensor-parallel-size 1Run GLM-4.6 with GGUF quantizations
Prebuilt GGUF weights published at unsloth/GLM-4.6-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/GLM-4.6-GGUFDeploy GLM-4.6 on Aquanode
Aquanode has no one-click deploy template for GLM-4.6; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (797 GB VRAM or more).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod