Deploy GLM-4.5-Air
GLM-4.5-Air by Z.ai on GPU capacity reserved for you: a private OpenAI-compatible endpoint, every request processed on European GPUs and logged in your audit trail, billed per GPU-hour on a monthly commitment.
- Maker
- Z.ai
- Params
- 110B
- Context
- 128K
- Architecture
- MoE · 128 experts, 8 active
- License
- MIT
- Released
- 2025-07-20
Footprint
Minimum to load the published checkpoint with a small KV cache. Long contexts and high concurrency need more; quantizing a 16-bit checkpoint needs less. You don't pick hardware on sference: you choose a performance tier and we size and run the deployment.
License
MITCommercial use allowed
Permissive: commercial use, modification, and private deployment allowed; keep the copyright notice. Read the license. Not legal advice.
FAQ
Can I run GLM-4.5-Air on a dedicated deployment in Europe?
Yes. sference deploys GLM-4.5-Air on GPU capacity reserved for you, behind a private endpoint, with every request processed on European GPUs and logged in your audit trail. Tell us your expected volume and latency targets with the form on this page and we come back with a sizing and a quote.
How many GPUs does GLM-4.5-Air need?
The published checkpoint is about 221 GB (BF16), so loading it takes at least 4 GPUs with 80 GB of memory each, or 2 GPUs with 141 GB each. Long contexts and high concurrency need more for the KV cache; quantization needs less. You don't pick hardware on sference: you choose a performance tier and we size the deployment.
Is GLM-4.5-Air licensed for commercial use?
GLM-4.5-Air is published under the MIT license. Permissive: commercial use, modification, and private deployment allowed; keep the copyright notice.
How is a dedicated deployment priced?
Per GPU-hour on a monthly commitment, sized to your throughput and latency targets.
Related models
Request GLM-4.5-Air
Tell us roughly how much traffic you expect. A fine-tune of GLM-4.5-Air? Mention it in the notes.
- 01We size it
A performance tier, the capacity behind it, and a quote for your volume.
- 02We benchmark it
Bring one workload with a sample of real traffic; we come back with latency and throughput numbers.
- 03It goes live
We provision the deployment. You call it with the same API and model id as before.
Specs from Hugging Face, synced 2026-10-27. Machine-readable version: https://sference.com/models/zai-org/GLM-4.5-Air.md