Granite 4.0 3B Vision BE needs about 3.0 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 1.5 GB (Q2_K) to 14.6 GB (F32).
Granite 4.0 3B Vision BE – a vision‑language model for complex document extraction
Granite 4.0 3B Vision BE is a LoRA adapter on top of Granite 4.0 Micro. It supports chart, table, and semantic key‑value pair extraction from document images. The base model handles text‑only requests without loading the adapter.
Good at
- Chart extraction to CSV or summary
- Table extraction with complex layouts
- Semantic key‑value pair extraction
Limits
- Requires 8 k context for estimates
- No vision support beyond document images
- Apache 2.0 license
Best for
- Enterprise document processing
- Data extraction pipelines
- Docling integration
Who it’s for. Developers building document analytics or extraction workflows that need robust chart and table understanding. The model can be used as a standalone VLM or combined with a text‑only base for hybrid workloads.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.5 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_M | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_L | 2.0 GB | 2.7 GB | Fits | Get file → | |
| IQ4_XS | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q4_0 | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 2.1 GB | 2.9 GB | Fits | Get file → | |
| IQ4_NL | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q4_1 | 2.3 GB | 3.1 GB | Fits | Get file → | |
| Q5_0 | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_M | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q5_1 | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q6_K | 3.0 GB | 3.9 GB | Fits | Get file → | |
| Q8_0 | 3.9 GB | 4.9 GB | Fits | Get file → | |
| BF16 | 7.3 GB | 8.7 GB | Too big | Get file → | |
| F16 | 7.3 GB | 8.7 GB | Too big | Get file → | |
| F32 | 14.6 GB | 16.9 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (file size 2.24 GB, memory 3 GB) is suitable. With 4 GB VRAM, Q3_K_S (1.68 GB, 2.4 GB memory) works. For larger budgets, Q4_1 (2.34 GB, 3.1 GB) or Q5_0 (2.55 GB, 3.4 GB) are options. Estimates are approximate.
What GPU do you need for Granite 4.0 3B Vision 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 Q6_K (3.0 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 4.9 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (7.3 GB file, about 8.7 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (7.3 GB file, about 8.7 GB in use).
- 24 GB VRAM: the best quant that fits is F32 (14.6 GB file, about 16.9 GB in use).
Which Granite 4.0 3B Vision BE quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 3B Vision BE: it balances file size and quality well. Here it is a 2.2 GB file.
The Q8_0 file is 3.9 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 1.5 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
Source
Frequently asked questions about Granite 4.0 3B Vision BE
How much VRAM does Granite 4.0 3B Vision BE need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 2.2 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 4.0 3B Vision BE on an 8 GB GPU?
Yes, with Q8_0: the 3.9 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 4.0 3B Vision BE GGUF?
It depends on the quant: Q2_K is 1.5 GB, Q3_K_S is 1.7 GB, Q3_K_M is 1.8 GB, Q3_K_L is 2.0 GB, IQ4_XS is 2.0 GB, Q4_0 is 2.1 GB and 13 more.
What context length does Granite 4.0 3B Vision BE support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download Granite 4.0 3B Vision BE GGUF?
The files are on Hugging Face in the taronaeo/Granite-4.0-3B-Vision-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 4.0 3B Vision 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 4.0 3B Vision BE on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 3 GB VRAM at 8 k context, which fits within 8 GB.
Does the model support image‑to‑text generation?
Yes, it can produce detailed natural‑language descriptions from images.
What license applies to this model?
The model is released under the Apache 2.0 license.