MobileVLM V2 1.7B needs about 2.9 GB of memory at Q4_K (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU.
MobileVLM V2 1.7B – a lightweight vision‑language model
MobileVLM V2 1.7B is a vision‑language model built on MobileLLaMA‑1.4B‑Chat. It supports image input and text generation with a 2048 token context. The model is released under the apache‑2.0 license.
Good at
- Vision‑language tasks
- Image captioning
- Visual question answering
Limits
- No vision support beyond images
- Limited to 2048 token context
- Requires 2.9 GB VRAM at 8K context
Best for
- Mobile deployment of VLMs
- Rapid prototyping of image‑text models
- Low‑resource inference
Who it’s for. Developers needing a small vision‑language model for mobile or edge devices. The model is suitable for applications that require image understanding and text generation without large GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.8 GB | 1.7 GB | Fits | Get file → |
The Q4_K quantization file is 0.79 GB and needs about 2.9 GB VRAM at 8K context. For 8 GB VRAM, Q4_K is suitable. If more memory is available, higher precision quants can be used, but they are not listed.
What GPU do you need for MobileVLM V2 1.7B?
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: the best quant that fits is Q4_K (0.8 GB file, about 2.9 GB in use).
Which MobileVLM V2 1.7B quant should you choose?
Q4_K (0.8 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 MobileVLM V2 1.7B
How much VRAM does MobileVLM V2 1.7B need?
About 2.9 GB at Q4_K with an 8K context window. That is the 0.8 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 MobileVLM V2 1.7B on an 8 GB GPU?
Yes, with Q4_K: the 0.8 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MobileVLM V2 1.7B GGUF?
It depends on the quant: Q4_K is 0.8 GB.
What context length does MobileVLM V2 1.7B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.
Where can I download MobileVLM V2 1.7B GGUF?
The files are on Hugging Face in the ZiangWu/MobileVLM_V2-1.7B-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 MobileVLM V2 1.7B 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 MobileVLM V2 1.7B on 8 GB VRAM?
Yes, the Q4_K quantization requires about 2.9 GB VRAM at 8K context, which fits within 8 GB.
Does this model support video input?
No, the model only supports image input as a vision capability.
What license does the model use?
The model is released under the apache‑2.0 license.