LLM
How to deploy GLM-5.2 on a GPU cloud
A 753B (MoE) language model for chat and instruction-following. Full specs, license and use cases.
GLM-5.2 size and hardware requirements
753.3B
Total parameters
Mixture-of-experts: 8 of 256 experts active per token (exact active-parameter count not stated on the model card)
Active parameters
BF16
Published precision
1683.8 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 1403.2 GB | 1683.8 GB | No capable live offer found | – | – |
| FP8 (quantized) | 701.6 GB | 841.9 GB | No capable live offer found | – | – |
| INT4 (quantized) | 350.8 GB | 421.0 GB | A100 | 6 | $5.10/hr |
How to run GLM-5.2
Run GLM-5.2 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-5.2 --tensor-parallel-size 1Run GLM-5.2 with Ollama
Verified against Ollama's own library listing.
ollama run glm-5.2Run GLM-5.2 with GGUF quantizations
Prebuilt GGUF weights published at unsloth/GLM-5.2-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/GLM-5.2-GGUFDeploy GLM-5.2 on Aquanode
Aquanode has no one-click deploy template for GLM-5.2; 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 (1684 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