GLM 4.7 Flash needs about 19.6 GB of memory at Q4_K (a 18.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 18.2 GB (Q4_K) to 31.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
GLM 4.7 Flash – a 30 B‑A3B MoE model for lightweight deployment
GLM 4.7 Flash is a 30 B‑A3B mixture‑of‑experts model based on the deepseek2 architecture. It is designed for efficient local inference while maintaining strong performance in the 30 B class. The model is released under the MIT license and supports inference via vLLM and SGLang.
Good at
- Large‑context generation up to 131 072 tokens
- Efficient MoE inference on modest GPUs
- Versatile language tasks with preserved thinking mode
Limits
- Requires 8 k context for memory estimates
- No vision capabilities
- Mixture‑of‑experts may need more VRAM than dense models
Best for
- Long‑form content creation
- Agentic multi‑turn dialogue
- Complex reasoning tasks
Who it’s for. Developers needing a balance between performance and resource usage for local deployment. Researchers working with 30 B‑class models who prefer an open‑source, MIT‑licensed option.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 18.2 GB | 19.6 GB | Too big | Get file → | |
| Q8_0 | 31.8 GB | 33.2 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K quantized file (18.24 GB, ~19.6 GB RAM at 8 k context). If more VRAM is available, the Q8_0 quant (31.84 GB, ~33.2 GB RAM) offers higher precision.
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K (18.2 GB file, about 19.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K (18.2 GB file, about 19.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (31.8 GB file, about 33.2 GB in use).
Which GLM 4.7 Flash quant should you choose?
Q4_K (18.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
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 19.6 GB at Q4_K with an 8K context window. That is the 18.2 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 19.6 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: Q4_K is 18.2 GB, Q8_0 is 31.8 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 0.8 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 ggml-org/GLM-4.7-Flash-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?
Yes, the Q4_K quantized file requires about 19.6 GB of RAM at 8 k context, which fits within 8 GB VRAM when using efficient memory mapping.
Does GLM 4.7 Flash support vision tasks?
No, the model does not include vision capabilities.