Z.ai - Mixture of experts - verified
Run GLM-5.3-Flash locally
GLM-5.3-Flash is a 321.3B mixture-of-experts (18B active) model from Z.ai with a 1.05M-token context window, released under MIT (commercial use is allowed); the smallest listed download is 199.7 GB, the UD-Q4_K_XL GGUF build from unsloth/GLM-5.3-Flash-GGUF.
Official weights: zai-org/GLM-5.3-Flash - modalities: text, image
- Total params
- 321.3B
- Active params
- 18B
- Context
- 1.05M
- Smallest download
- 199.7 GB
Fits in
Smallest download at most 85% of memoryDownloads
The official weights and every quantization listed for this model, with file sizes from Hugging Face.
| Download | Format | Size | Repo |
|---|---|---|---|
Official weights | FP8 | 328.3 GB | zai-org/GLM-5.3-Flash |
UD-Q4_K_XLSmallest listed | GGUF | 199.7 GB | unsloth/GLM-5.3-Flash-GGUF |
Q8_0 | GGUF | 341.0 GB | unsloth/GLM-5.3-Flash-GGUF |
4bit | MLX | 204.0 GB | mlx-community/GLM-5.3-Flash-4bit |
GB is decimal: 1 GB = 10^9 bytes. Add memory for the context and the operating system on top of the file size.
Run it
The official pages read for this directory publish no copyable run command for GLM-5.3-Flash. Download the weights from zai-org/GLM-5.3-Flash and follow the model card's serving instructions.
Not sure which runtime to use? Compare local LLM runtimes by platform, API and features.
License
- License
- MIT
mit - Commercial use
- Commercial use: YesCommercial use is allowed.
- Gated download
- No. The files download directly.
Worth knowing
Natively multimodal MoE with hybrid sparse and linear attention, 320B total and 18B active parameters per the card.
Released (per the announcement).
FAQ
How big is the GLM-5.3-Flash download?
The official FP8 weights in zai-org/GLM-5.3-Flash are 328.3 GB. The smallest listed download is 199.7 GB, the UD-Q4_K_XL GGUF build from unsloth/GLM-5.3-Flash-GGUF. Plan for more memory than the file size: the context (KV cache) and the operating system need room too.
Can I use GLM-5.3-Flash commercially?
GLM-5.3-Flash is released under MIT, and commercial use is allowed. The license text is at https://huggingface.co/zai-org/GLM-5.3-Flash/blob/main/LICENSE.
How much memory do I need for GLM-5.3-Flash?
By this directory's rule of thumb it fits in 256 GB and up: the smallest listed download, 199.7 GB, is at most 85% of 256 GB, which leaves room for the context and the operating system.
What is the context length of GLM-5.3-Flash?
1,048,576 tokens. A longer context needs more memory for the KV cache, so you can run with a shorter one when memory is tight.
Sources
Last verified from the pages below.
- Hugging Face model card - huggingface.co
- config.json - huggingface.co
- Z.ai announcement - z.ai
- unsloth GGUF - huggingface.co
- MLX 4-bit - huggingface.co
Newsletter
New open weights, every week
One email per week. New model releases, open-weight drops and what they mean for what you build.
Keep exploring
Best local AI models
Our curated picks by hardware tier, with benchmarks and the reasoning.
Model API pricing and specs
First-party prices per 1M tokens when you would rather call an API.
AI benchmark leaderboards
Sourced scores, for when you need to compare quality.
Setup guides
Point your coding tools at the model you picked.