Glm-4.7-Flash needs about 20.5 GB of memory at its main file (a 19.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 11.9 GB to 22.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
GLM‑4.7‑Flash: 30B‑A3B MoE model for lightweight deployment
GLM‑4.7‑Flash is a 30B‑A3B Mixture‑of‑Experts model based on the deepseek2 architecture. It offers a balance of performance and efficiency for local inference. The model is released under the Apache‑2.0 license.
Good at
- Large‑context generation
- Multi‑turn agentic tasks
- High‑capacity reasoning
Limits
- Requires 8‑k context for memory estimates
- No vision support
- Mixture‑of‑Experts architecture may limit single‑GPU deployment
Best for
- Chatbots needing long context
- Agentic task automation
- Research prototyping
Who it’s for. Developers and researchers who need a 30B‑class MoE model that can run locally with moderate VRAM. The model is suitable for those who prefer open‑source licensing and can handle the memory demands of MoE inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 11.9 GB | 13.3 GB | Too big | Get file → | |
| — | 14.6 GB | 15.9 GB | Too big | Get file → | |
| — | 14.6 GB | 15.9 GB | Too big | Get file → | |
| — | 19.2 GB | 20.5 GB | Too big | Get file → | |
| — | 19.2 GB | 20.5 GB | Too big | Get file → | |
| — | 22.1 GB | 23.4 GB | Too big | Get file → | |
| — | 22.1 GB | 23.4 GB | Too big | Get file → |
For 8‑GB VRAM, use the 11.93‑GB file (est. 13.3‑GB memory at 8k context). For 16‑GB VRAM, the 14.58‑GB file (est. 15.9‑GB memory) is suitable. For larger VRAM, the 22.05‑GB file (est. 23.4‑GB memory) provides the best performance.
What GPU do you need for Glm-4.7-Flash?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is the main file (14.6 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (22.1 GB file, about 23.4 GB in use).
Which Glm-4.7-Flash quant should you choose?
If memory is tight, the smallest file is the first one in the table at 11.9 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Glm-4.7-Flash
How much VRAM does Glm-4.7-Flash need?
About 20.5 GB at its main file with an 8K context window. That is the 19.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Glm-4.7-Flash on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Glm-4.7-Flash GGUF?
It depends on the quant: file is 11.9 GB, file is 14.6 GB, file is 14.6 GB, file is 19.2 GB, file is 19.2 GB, file is 22.1 GB and 1 more.
What context length does Glm-4.7-Flash support?
The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.
Where can I download Glm-4.7-Flash GGUF?
The files are on Hugging Face in the mudler/GLM-4.7-Flash-APEX-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Glm-4.7-Flash use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run GLM‑4.7‑Flash on 8 GB VRAM?
The 11.93‑GB GGUF file estimates 13.3‑GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.
Does GLM‑4.7‑Flash support vision tasks?
No, the model has no vision capabilities.