QW

qwen2vl vision

QwenGGUF by LiuHao03322Updated 2024-11-11
Download on Hugging Face
Parameters665M
Context—
Layers—
Architectureclip
Smallest quant2.7 GB
Quick answer

qwen2vl vision needs about 3.5 GB of memory at its main file (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.

qwen2vl vision is a 665M-parameter Qwen model in GGUF format, quantized by LiuHao03322. The repository has 1 quant file, from 2.7 GB to 2.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.7 GB 3.5 GB
Fits Get file →

What GPU do you need for qwen2vl vision?

These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (2.7 GB file, about 3.5 GB in use).

Specifications

Architecture from the GGUF header

Architectureclip
Parameters665M

Source

Quantized byLiuHao03322
FamilyQwen
Licenseapache-2.0
Downloads (HF)28
Last updated2024-11-11

Frequently asked questions about qwen2vl vision

How much VRAM does qwen2vl vision need?

About 3.5 GB at its main file with an 8K context window. That is the 2.7 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 qwen2vl vision on an 8 GB GPU?

Yes, with the smaller files: the 2.7 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of qwen2vl vision GGUF?

It depends on the quant: file is 2.7 GB.

Where can I download qwen2vl vision GGUF?

The files are on Hugging Face in the LiuHao03322/qwen2vl-vision.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 qwen2vl vision 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.

Similar models

Browse all →

More from LiuHao03322

All by LiuHao03322 →

More Qwen models

All Qwen →

Other tiny models

All tiny models →