Qwen2-VL-2B-Instruct 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. This repository has 2 quants, from 2.7 GB to 3.1 GB (F16).
Qwen2-VL-2B-Instruct is a 1.54B-parameter Qwen model in GGUF format, quantized by sidrajaram. Its trained context length is 32K tokens. The repository has 2 quant files, from 2.7 GB to 3.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.7 GB | 3.5 GB | Fits | Get file → | |
| F16 | 3.1 GB | 4.0 GB | Fits | Get file → |
What GPU do you need for Qwen2-VL-2B-Instruct?
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 F16 (3.1 GB file, about 4.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen2-VL-2B-Instruct
How much VRAM does Qwen2-VL-2B-Instruct 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 Qwen2-VL-2B-Instruct on an 8 GB GPU?
Yes, with F16: the 3.1 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen2-VL-2B-Instruct GGUF?
It depends on the quant: file is 2.7 GB, F16 is 3.1 GB.
What context length does Qwen2-VL-2B-Instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K).
Where can I download Qwen2-VL-2B-Instruct GGUF?
The files are on Hugging Face in the sidrajaram/Qwen2-VL-2B-Instruct-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 Qwen2-VL-2B-Instruct 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.