Granite Vision 3.2 2b needs about 2.7 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.4 GB (Q3_K_L) to 2.7 GB (Q8_0).
Granite Vision 3.2 2b – compact vision‑language model for document understanding
Granite Vision 3.2 2b is a 2.53 billion parameter model designed for visual document understanding. It supports English instructions and image inputs such as png and jpeg. The model is trained on curated instruction‑following data for tables, charts, infographics, and general image tasks.
Good at
- Table and chart extraction
- OCR and document QA
- General image understanding
Limits
- No vision support beyond images
- Requires 16k token context
- Apache‑2.0 license
Best for
- Enterprise document processing
- Automated data extraction
- Business image analysis
Who it’s for. Developers building enterprise applications that need to process visual and textual data. The model is suitable for tasks involving tables, charts, OCR, and general image queries. For pure text tasks, a Granite large language model is recommended.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 1.4 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 3.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q3_K_L (file size 1.36 GB, estimated 2.5 GB memory). For 12 GB VRAM, Q4_K_M (1.55 GB, 2.7 GB memory) is suitable. For 16 GB VRAM, Q6_K (2.08 GB, 3.3 GB memory) or Q8_0 (2.69 GB, 3.9 GB memory) can be used. Memory estimates are approximate.
What GPU do you need for Granite Vision 3.2 2b?
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 Q8_0 (2.7 GB file, about 3.9 GB in use).
Which Granite Vision 3.2 2b quant should you choose?
Q4_K_M is the usual starting point for Granite Vision 3.2 2b: it balances file size and quality well. Here it is a 1.5 GB file.
The Q8_0 file is 2.7 GB, about 1.7 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.
If memory is tight, the smallest file is Q3_K_L at 1.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Granite Vision 3.2 2b
How much VRAM does Granite Vision 3.2 2b need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.5 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 Granite Vision 3.2 2b on an 8 GB GPU?
Yes, with Q8_0: the 2.7 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite Vision 3.2 2b GGUF?
It depends on the quant: Q3_K_L is 1.4 GB, Q4_K_M is 1.5 GB, Q6_K is 2.1 GB, Q8_0 is 2.7 GB.
What context length does Granite Vision 3.2 2b support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.7 GB at 8K and 1.3 GB at 16K.
Where can I download Granite Vision 3.2 2b GGUF?
The files are on Hugging Face in the lmstudio-community/granite-vision-3.2-2b-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 Granite Vision 3.2 2b 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 Granite Vision 3.2 2b on 8 GB VRAM?
Yes, the Q3_K_L quantization requires about 2.5 GB VRAM at 8k context, which fits within an 8 GB GPU.
Does the model support image formats other than png and jpeg?
The model accepts png and jpeg images; other formats are not guaranteed to work.
Is the model licensed for commercial use?
It is released under Apache‑2.0, which allows commercial use with attribution.