GR

Granite Vision 4.1 4B BE

GraniteGGUF by taronaeoUpdated 2026-10-18
Download on Hugging Face
Parameters3.4B
Context128K
Layers—
Architecturegranite
Smallest quant1.4 GB
Quick answer

Granite Vision 4.1 4B BE needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 1.4 GB (Q2_K) to 13.6 GB (F32).

Granite Vision 4.1 4B BE – lightweight vision‑language model for document extraction

Granite Vision 4.1 4B BE is a 3.4B parameter VLM optimized for structured document extraction. It supports chart, table, and semantic key‑value pair extraction with a 131072 token context window. The model is released under Apache 2.0.

Good at

  • Chart extraction to CSV or summary
  • Table extraction with complex layouts
  • Semantic key‑value pair extraction

Limits

  • No vision support beyond document images
  • Requires 8 k context for memory estimates
  • No other vision‑language tasks beyond described

Best for

  • Document processing pipelines
  • Automated chart analysis
  • Table extraction from scanned PDFs

Who it’s for. Developers building document intelligence solutions who need efficient extraction of charts, tables, and key‑value pairs. The model integrates with Docling and can be used standalone.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 2.0 GB
Fits Get file →
Q3_K_S1.6 GB 2.3 GB
Fits Get file →
Q3_K_M1.7 GB 2.4 GB
Fits Get file →
Q3_K_L1.9 GB 2.6 GB
Fits Get file →
IQ4_XS1.9 GB 2.6 GB
Fits Get file →
Q4_02.0 GB 2.7 GB
Fits Get file →
Q4_K_S2.0 GB 2.7 GB
Fits Get file →
IQ4_NL2.0 GB 2.7 GB
Fits Get file →
Q4_K_M2.1 GB 2.9 GB
Fits Get file →
Q4_12.2 GB 2.9 GB
Fits Get file →
Q5_02.4 GB 3.2 GB
Fits Get file →
Q5_K_S2.4 GB 3.2 GB
Fits Get file →
Q5_K_M2.4 GB 3.2 GB
Fits Get file →
Q5_12.6 GB 3.4 GB
Fits Get file →
Q6_K2.8 GB 3.6 GB
Fits Get file →
Q8_03.6 GB 4.6 GB
Fits Get file →
BF166.8 GB 8.1 GB
Too big Get file →
F166.8 GB 8.1 GB
Too big Get file →
F3213.6 GB 15.7 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (2.1 GB file, 2.9 GB memory). For 4 GB VRAM use Q3_K_S (1.57 GB file, 2.3 GB memory). For 2 GB VRAM use Q2_K (1.37 GB file, 2 GB memory).

What GPU do you need for Granite Vision 4.1 4B 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 (2.8 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.6 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 8.1 GB in use).
  • 16 GB VRAM: the best quant that fits is F32 (13.6 GB file, about 15.7 GB in use).

Which Granite Vision 4.1 4B BE quant should you choose?

Q4_K_M is the usual starting point for Granite Vision 4.1 4B BE: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.6 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 1.4 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
Parameters3.4B
Trained context131,072 tokens

Source

Quantized bytaronaeo
FamilyGranite
Licenseapache-2.0
Downloads (HF)787
Last updated2026-10-18

Frequently asked questions about Granite Vision 4.1 4B BE

How much VRAM does Granite Vision 4.1 4B BE need?

About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 4.1 4B BE on an 8 GB GPU?

Yes, with Q8_0: the 3.6 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite Vision 4.1 4B BE GGUF?

It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.6 GB, Q3_K_M is 1.7 GB, Q3_K_L is 1.9 GB, IQ4_XS is 1.9 GB, Q4_0 is 2.0 GB and 13 more.

What context length does Granite Vision 4.1 4B BE support?

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

Where can I download Granite Vision 4.1 4B BE GGUF?

The files are on Hugging Face in the taronaeo/Granite-Vision-4.1-4B-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 4.1 4B 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 4.1 4B BE on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S quantizations will fit within 8 GB VRAM with approximate memory usage of 2.9 GB or 2.7 GB respectively.

Does the model support image‑to‑text generation?

Yes, it can produce detailed natural‑language descriptions from images as part of its vision‑language capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-vision-4.1-4b

Similar models

Browse all →

More from taronaeo

All by taronaeo →

More Granite models

All Granite →

Other tiny models

All tiny models →