GLM-5.3-Flash
Hugging Face (zai-org) Open weights
The catch: A 320B-parameter download, and the card gives no hardware figure or serve command, only SGLang and vLLM recipe links; Ollama offers it only as a cloud tag.
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. MIT, so no user cap or revenue clause (unlike GLM-5.3). 320B total / 18B active parameters (MoE with hybrid sparse and linear attention); the first natively multimodal GLM-5 model. |
| Modality | text, code, image |
| Credit card | Not required |
| Commercial use | Allowed |
| Trains on your data | – |
| Licence or terms | MIT |
| Context window | 1,048,576 tokens |
| Model id | zai-org/GLM-5.3-Flash |
| Base URL | – |
| Last checked | 2 Oct 2026 |
How to use GLM-5.3-Flash
Download the weights and serve them yourself. Licence: MIT.
Paste into Claude Code
I want to run the open-weight model "GLM-5.3-Flash" (zai-org/GLM-5.3-Flash) for my project. Please: 1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint). 2. Give me a minimal working setup and a test request. 3. Tell me the licence terms for commercial use. 4. If a cheaper or smaller variant would do the job, mention it.
Before you ship on it
- A 320B-parameter download, and the card gives no hardware figure or serve command, only SGLang and vLLM recipe links; Ollama offers it only as a cloud tag.
- Plain MIT License (LICENSE in the HF repo, copyright 2026 Z.AI): use, copy, modify and sell freely as long as the copyright and permission notice is kept.
- Free to run means you pay for the GPUs, the serving stack and the on-call.
Questions
Is GLM-5.3-Flash free?
Yes. Open weights offers it as open weights, with these limits: Self-host free · MIT. No credit card is needed.
Can I use GLM-5.3-Flash commercially?
Yes, under MIT. Check the current terms before you ship.
How do I start with GLM-5.3-Flash?
Download the weights and serve them yourself. Licence: MIT.
Source: huggingface.co/zai-org/GLM-5.3-Flash, checked 2 Oct 2026.