GR

Granite Vision 3.2 2B BE

GraniteGGUF by taronaeoUpdated 2026-10-18
Download on Hugging Face
Parameters2.53B
Context128K
Layers—
Architecturegranite
Smallest quant1.0 GB
Quick answer

Granite Vision 3.2 2B BE needs about 2.2 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 19 quants, from 1.0 GB (Q2_K) to 10.1 GB (F32).

Granite Vision 3.2 2B BE – compact vision‑language model for document understanding

Granite Vision 3.2 2B BE is a 2.53B parameter model fine‑tuned for visual document tasks. It processes English instructions and images such as png and jpeg. The model is licensed under Apache 2.0 and is suitable for enterprise document analysis.

Good at

  • Table and chart extraction
  • OCR and text extraction
  • General image question answering

Limits

  • No vision support beyond images
  • Limited to English instructions
  • Requires 8 k context for estimates

Best for

  • Automated invoice processing
  • Business report analysis
  • Visual data extraction in enterprise workflows

Who it’s for. Developers building enterprise applications that need to analyze documents and images. The model is ideal for teams that require efficient, open‑source multimodal processing without extensive GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.6 GB
Fits Get file →
Q3_K_S1.1 GB 1.8 GB
Fits Get file →
Q3_K_M1.3 GB 1.9 GB
Fits Get file →
Q3_K_L1.4 GB 2.0 GB
Fits Get file →
IQ4_XS1.4 GB 2.1 GB
Fits Get file →
Q4_01.5 GB 2.1 GB
Fits Get file →
Q4_K_S1.5 GB 2.1 GB
Fits Get file →
IQ4_NL1.5 GB 2.1 GB
Fits Get file →
Q4_K_M1.5 GB 2.2 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
Q5_01.8 GB 2.5 GB
Fits Get file →
Q5_K_S1.8 GB 2.5 GB
Fits Get file →
Q5_K_M1.8 GB 2.5 GB
Fits Get file →
Q5_11.9 GB 2.6 GB
Fits Get file →
Q6_K2.1 GB 2.8 GB
Fits Get file →
Q8_02.7 GB 3.5 GB
Fits Get file →
BF165.1 GB 6.2 GB
Fits Get file →
F165.1 GB 6.2 GB
Fits Get file →
F3210.1 GB 11.9 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (est. 2.2 GB) or Q4_1 (2.3 GB). With 12 GB VRAM Q5_0 (2.5 GB) or Q5_K_S (2.5 GB) are suitable. For 16 GB VRAM Q6_K (2.8 GB) or Q8_0 (3.5 GB) provide higher quality.

What GPU do you need for Granite Vision 3.2 2B BE?

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 Q8_0 (2.7 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.5 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.1 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is F32 (10.1 GB file, about 11.9 GB in use).

Which Granite Vision 3.2 2B BE quant should you choose?

Q4_K_M is the usual starting point for Granite Vision 3.2 2B BE: 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 Q2_K at 1.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters2.53B
Trained context131,072 tokens

Source

Quantized bytaronaeo
FamilyGranite
Licenseapache-2.0
Downloads (HF)863
Last updated2026-10-18

Frequently asked questions about Granite Vision 3.2 2B BE

How much VRAM does Granite Vision 3.2 2B BE need?

About 2.2 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 BE on an 8 GB GPU?

Yes, with BF16: the 5.1 GB file needs about 6.2 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 BE GGUF?

It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.1 GB, Q3_K_M is 1.3 GB, Q3_K_L is 1.4 GB, IQ4_XS is 1.4 GB, Q4_0 is 1.5 GB and 13 more.

What context length does Granite Vision 3.2 2B BE support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download Granite Vision 3.2 2B BE GGUF?

The files are on Hugging Face in the taronaeo/Granite-Vision-3.2-2B-BE-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 BE 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 BE on 8 GB VRAM?

Yes, use the Q4_K_M or Q4_1 quantized files which require about 2.2–2.3 GB of VRAM at 8 k context.

Does the model support languages other than English?

The current model only supports English instructions and image inputs.

Is the model free to use?

Yes, it is released under the Apache 2.0 license and can be used without cost.

Other GGUFs of granite-vision-3.2-2b

Similar models

Browse all →

More from taronaeo

All by taronaeo →

More Granite models

All Granite →

Other tiny models

All tiny models →