# Deploy Z.ai models on dedicated GPUs

16 Z.ai models ready to deploy on GPU capacity reserved for you, from 2.3B to 754B parameters, covering chat & reasoning, vision & multimodal and speech recognition. Private OpenAI-compatible endpoint, European GPUs, billed per GPU-hour.

| Model | Type | Params | Context | License | Page |
| --- | --- | --- | --- | --- | --- |
| GLM-5.3-Flash | Chat & reasoning | 321B | 1M | MIT | https://sference.com/models/zai-org/GLM-5.3-Flash.md |
| GLM-5.3 | Chat & reasoning | 753B | 1M | Custom license | https://sference.com/models/zai-org/GLM-5.3.md |
| GLM-5.2 | Chat & reasoning | 753B | 1M | MIT | https://sference.com/models/zai-org/GLM-5.2.md |
| GLM-4.7-Flash | Chat & reasoning | 31B | 195K | MIT | https://sference.com/models/zai-org/GLM-4.7-Flash.md |
| GLM-5.1 | Chat & reasoning | 754B | 200K | MIT | https://sference.com/models/zai-org/GLM-5.1.md |
| GLM-4.7 | Chat & reasoning | 358B | 200K | MIT | https://sference.com/models/zai-org/GLM-4.7.md |
| GLM-5 | Chat & reasoning | 754B | 200K | MIT | https://sference.com/models/zai-org/GLM-5.md |
| GLM-4.6 | Chat & reasoning | 357B | 200K | MIT | https://sference.com/models/zai-org/GLM-4.6.md |
| GLM-4.5 | Chat & reasoning | 358B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.5.md |
| GLM-4.5-Air | Chat & reasoning | 110B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.5-Air.md |
| GLM-4.5V | Vision & multimodal | 108B | 64K | MIT | https://sference.com/models/zai-org/GLM-4.5V.md |
| GLM-4.1V-9B-Thinking | Vision & multimodal | 10B | 64K | MIT | https://sference.com/models/zai-org/GLM-4.1V-9B-Thinking.md |
| GLM-4.6V-Flash | Vision & multimodal | 10B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.6V-Flash.md |
| GLM-4-32B-0414 | Chat & reasoning | 33B | 32K | MIT | https://sference.com/models/zai-org/GLM-4-32B-0414.md |
| GLM-ASR-Nano-2512 | Speech recognition | 2.3B | 8K | MIT | https://sference.com/models/zai-org/GLM-ASR-Nano-2512.md |
| GLM-4.6V | Vision & multimodal | 108B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.6V.md |

## FAQ

### Which Z.ai models can I deploy on sference?

16 today, most requested first: GLM-5.3-Flash, GLM-5.3, GLM-5.2, GLM-4.7-Flash, GLM-5.1, GLM-4.7, GLM-5 and GLM-4.6, and 8 more. Any other Z.ai checkpoint or a fine-tune of one can be requested with the form on this page.

### How many GPUs do Z.ai models need?

It depends on the model: the lineup runs from 2.3B to 754B parameters. Each model page lists the checkpoint size and the minimum footprint on 80 GB and 141 GB GPUs. You don't pick hardware on sference: you choose a performance tier and we size the deployment.

### Can I use Z.ai models commercially?

15 of the 16 listed models are under licenses that allow commercial use (MIT and Custom license across the lineup). Each model page summarizes its license and links the full text.

### How is a dedicated deployment priced?

Per GPU-hour on a monthly commitment, sized to your throughput and latency targets.

Request a deployment: https://sference.com/models/zai-org#request. All makers: https://sference.com/dedicated.md