GR

granite vision 3.2 2b

GraniteGGUF by ibm-researchUpdated 2025-03-03
Download on Hugging Face
Parameters2.53B
Context16K
Layers40
Architecturegranite
Smallest quant1.5 GB
Quick answer

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 1.5 GB (Q4_K_M) to 5.1 GB (F16).

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

Granite Vision 3.2 2B is a 2.53 billion‑parameter vision‑language model trained on instruction‑following data. It excels at extracting information from tables, charts, infographics, and general image tasks. The model is released under Apache 2.0 and supports English instructions with image inputs.

Good at

  • Document OCR and table extraction
  • Chart and infographic analysis
  • General image question answering

Limits

  • No support for non‑English instructions
  • Requires image input, no text‑only mode
  • Limited to 16384 context tokens

Best for

  • Enterprise document processing
  • Automated data extraction from PDFs
  • Visual QA in business workflows

Who it’s for. Developers building enterprise applications that need to process visual and textual data. Ideal for teams requiring efficient, open‑source multimodal models for document understanding and general image tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.5 GB 2.7 GB
Fits Get file →
Q5_K_M1.8 GB 3.0 GB
Fits Get file →
Q8_02.7 GB 3.9 GB
Fits Get file →
F165.1 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.55 GB, ~2.7 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (1.8 GB, ~3 GB memory). For 16 GB VRAM, Q8_0 (2.69 GB, ~3.9 GB memory). F16 requires ~5.07 GB and ~6.2 GB memory, suitable for larger GPUs.

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).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.1 GB file, about 6.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters2.53B
Layers40
Trained context16,384 tokens
KV cache (fp16)80 KB per token

Source

Quantized byibm-research
FamilyGranite
Licenseapache-2.0
Downloads (HF)845
Last updated2025-03-03

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 F16: 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 GGUF?

It depends on the quant: Q4_K_M is 1.5 GB, Q5_K_M is 1.8 GB, Q8_0 is 2.7 GB, F16 is 5.1 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 ibm-research/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 Q4_K_M quantization is 1.55 GB and uses about 2.7 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision tasks other than document analysis?

Yes, it can perform general image understanding and answer visual questions beyond documents.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-vision-3.2-2b

Similar models

Browse all →

More from ibm-research

All by ibm-research →

More Granite models

All Granite →

Other tiny models

All tiny models →