GLM 4.6V Flash needs about 7.0 GB of memory at Q4_K_M (a 6.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 6.2 GB (Q4_K_M) to 10.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.
GLM 4.6V Flash – 9.4 B multimodal model for local deployment
GLM 4.6V Flash is a 9.4 B parameter model in the GLM family. It supports vision and has a 128k‑token training context. The model is released under the MIT license and is optimized for low‑latency local use.
Good at
- Vision‑enabled multimodal reasoning
- Native function calling with images
- Interleaved image‑text generation
Limits
- Requires 8 k context for memory estimates
- No explicit language list provided
- No separate vision‑only mode
Best for
- Local multimodal assistants
- Image‑text content creation
- Document understanding with visual data
Who it’s for. Developers building local multimodal agents who need a lightweight model with vision and function‑calling support. The model is suitable for edge or desktop deployments where GPU memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 6.2 GB | 7.0 GB | Fits | Get file → | |
| Q8_0 | 10.0 GB | 10.8 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quantization (6.17 GB file, ~7 GB RAM at 8 k context). If more memory is available, Q8_0 (10 GB file, ~10.8 GB RAM) provides higher precision. Estimates are approximate.
What GPU do you need for GLM 4.6V 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: the best quant that fits is Q4_K_M (6.2 GB file, about 7.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 10.8 GB in use).
Which GLM 4.6V Flash quant should you choose?
Q4_K_M is the usual starting point for GLM 4.6V Flash: it balances file size and quality well. Here it is a 6.2 GB file.
The Q8_0 file is 10.0 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 4.6V Flash
How much VRAM does GLM 4.6V Flash need?
About 7.0 GB at Q4_K_M with an 8K context window. That is the 6.2 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 4.6V Flash on an 8 GB GPU?
Yes, with Q4_K_M: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 4.6V Flash GGUF?
It depends on the quant: Q4_K_M is 6.2 GB, Q8_0 is 10.0 GB.
What context length does GLM 4.6V Flash support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.3 GB at 32K.
Where can I download GLM 4.6V Flash GGUF?
The files are on Hugging Face in the ggml-org/GLM-4.6V-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 4.6V 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 4.6V Flash on 8 GB VRAM?
Yes, using the Q4_K_M quantization the model requires about 7 GB of RAM at 8 k context, fitting within an 8 GB VRAM budget.
Does the model support vision?
Yes, GLM 4.6V Flash has native vision capabilities and can process images directly.
What license applies to this model?
The model is released under the MIT license, allowing free use and modification.