GLM 4.7 Flash needs about 14.6 GB of memory at its main file (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.2 GB to 16.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
GLM 4.7 Flash – 31.2B MoE model for lightweight deployment
GLM 4.7 Flash is a 31.2B‑parameter MoE model based on the deepseek2 architecture. It offers a balance between performance and efficiency for local inference. The model is released under the MIT license and supports reasoning and tools usage.
Good at
- Reasoning
- Tools integration
- Long‑context handling
Limits
- No vision support
- Requires llama.cpp `b10251` or newer
- Large VRAM requirement for full context
Best for
- Agentic tasks
- Long‑form generation
- Complex reasoning workflows
Who it’s for. Developers and researchers who need a large‑scale MoE model that can be run locally with moderate hardware. The model is suitable for applications requiring advanced reasoning and tool usage within a single‑process environment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 10.2 GB | 11.6 GB | Too big | Get file → | |
| — | 13.3 GB | 14.6 GB | Too big | Get file → | |
| — | 16.6 GB | 18.0 GB | Too big | Get file → |
The available GGUF files are all quantized with an unknown quant scheme. The smallest file is 10.24 GB and requires approximately 11.6 GB of VRAM at an 8 k context. The 13.27 GB file needs about 14.6 GB of VRAM, and the 16.6 GB file requires roughly 18 GB of VRAM. Choose the file that fits your VRAM budget.
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: the best quant that fits is the main file (10.2 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (13.3 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (16.6 GB file, about 18.0 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 10.2 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 14.6 GB at its main file with an 8K context window. That is the 13.3 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 11.6 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 10.2 GB, file is 13.3 GB, file is 16.6 GB.
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 0.9 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 Myric/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 mit. 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?
No. The smallest GGUF file requires 11.6 GB of VRAM at an 8 k context, so 8 GB is insufficient.
Does GLM 4.7 Flash support vision tasks?
No. The model has no vision capabilities.