GR

Granite Vision 4.1 4b

GraniteGGUF by ibm-graniteUpdated 2026-06-24
Download on Hugging Face
Parameters3.4B
Context128K
Layers40
Architecturegranite
Smallest quant2.1 GB
Quick answer

Granite Vision 4.1 4b needs about 3.3 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 5 quants, from 2.1 GB (Q4_K_M) to 6.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

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

Granite Vision 4.1 4B is a 3.4B parameter VLM optimized for structured document extraction. It supports chart, table, and key‑value pair extraction while also providing image‑to‑text capabilities. The model is released under Apache 2.0 and is available in multiple GGUF quantizations.

Good at

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

Limits

  • No vision support beyond image‑to‑text
  • Requires 8 k context for estimates
  • No explicit language support listed

Best for

  • Document processing pipelines
  • Data extraction from scanned reports
  • Automated form analysis

Who it’s for. Developers building document‑centric AI solutions who need a lightweight VLM. The model integrates with Docling and can be used standalone via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.1 GB 3.3 GB
Fits Get file →
Q5_K_M2.4 GB 3.6 GB
Fits Get file →
Q6_K2.8 GB 4.0 GB
Fits Get file →
Q8_03.6 GB 4.8 GB
Fits Get file →
BF166.8 GB 8.0 GB
Tight Get file →

For 8 GB VRAM use Q4_K_M (file size 2.1 GB, estimated 3.3 GB memory). For 12 GB VRAM Q5_K_M (2.44 GB, 3.6 GB). For 16 GB VRAM Q6_K (2.8 GB, 4 GB).

What GPU do you need for Granite Vision 4.1 4b?

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 Q6_K (2.8 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 8.0 GB in use).

Which Granite Vision 4.1 4b quant should you choose?

Q4_K_M is the usual starting point for Granite Vision 4.1 4b: 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters3.4B
Layers40
Trained context131,072 tokens
KV cache (fp16)80 KB per token

Source

Quantized byibm-granite
FamilyGranite
Licenseapache-2.0
Downloads (HF)7,551
Last updated2026-06-24

Frequently asked questions about Granite Vision 4.1 4b

How much VRAM does Granite Vision 4.1 4b need?

About 3.3 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 on an 8 GB GPU?

Yes, with BF16: the 6.8 GB file needs about 8.0 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 GGUF?

It depends on the quant: Q4_K_M is 2.1 GB, Q5_K_M is 2.4 GB, Q6_K is 2.8 GB, Q8_0 is 3.6 GB, BF16 is 6.8 GB.

What context length does Granite Vision 4.1 4b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Granite Vision 4.1 4b GGUF?

The files are on Hugging Face in the ibm-granite/granite-vision-4.1-4b-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 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 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 3.3 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support text generation?

The model supports image‑to‑text tasks but is primarily tuned for structured document extraction.

What license applies to the 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 ibm-granite

All by ibm-granite →

More Granite models

All Granite →

Other tiny models

All tiny models →