GLM 4.7 Flash DASHQ Q2 needs about 12.1 GB of memory at IQ2_M (a 10.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.2 GB (IQ2_XXS) to 11.5 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
GLM 4.7 Flash DASHQ Q2 – 29.9B‑parameter MoE model
GLM 4.7 Flash is a 29.9B‑parameter MoE model from the GLM family. It is quantized to 2‑bit using DASH‑Q and supports inference via llama.cpp. The model is released under the MIT license.
Good at
- Instruction following
- Reasoning tasks
- Multi‑turn dialogue
Limits
- No vision support
- Requires 8k context for memory estimates
- Large VRAM needed for full precision
Best for
- Local deployment on high‑VRAM GPUs
- Research prototyping
- Fine‑tuning with llama.cpp
Who it’s for. Developers and researchers who need a lightweight 30B‑class MoE model for local inference. The model is suitable for those who can manage the memory requirements of a 2‑bit quantized version.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 10.2 GB | 11.6 GB | Too big | Get file → | |
| IQ2_M | 10.7 GB | 12.1 GB | Too big | Get file → | |
| Q2_K_XL | 11.5 GB | 12.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (10.25 GB file, 11.6 GB memory at 8k context). For 12 GB VRAM, IQ2_M (10.73 GB file, 12.1 GB memory) is suitable. If you have 16 GB VRAM, Q2_K_XL (11.55 GB file, 12.9 GB memory) provides a higher quality option. Memory estimates are approximate.
What GPU do you need for GLM 4.7 Flash DASHQ Q2?
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 IQ2_XXS (10.2 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K_XL (11.5 GB file, about 12.9 GB in use).
Which GLM 4.7 Flash DASHQ Q2 quant should you choose?
IQ2_M (10.7 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is IQ2_XXS at 10.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 4.7 Flash DASHQ Q2
How much VRAM does GLM 4.7 Flash DASHQ Q2 need?
About 12.1 GB at IQ2_M with an 8K context window. That is the 10.7 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 DASHQ Q2 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 DASHQ Q2 GGUF?
It depends on the quant: IQ2_XXS is 10.2 GB, IQ2_M is 10.7 GB, Q2_K_XL is 11.5 GB.
What context length does GLM 4.7 Flash DASHQ Q2 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 DASHQ Q2 GGUF?
The files are on Hugging Face in the jkim96/GLM-4.7-Flash-DASHQ-Q2-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 DASHQ Q2 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 IQ2_XXS quantized file is 10.25 GB and requires about 11.6 GB memory at 8k context, which fits an 8 GB VRAM setup with some overhead.
Does this model support vision tasks?
No, the model has no vision capabilities and is designed for text-only inference.
What license does the model use?
The model is released under the MIT license, inherited from the parent GLM-4.7-Flash model.