GR

granite vision crispembed

GraniteGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters—
Context—
Layers—
Architecturegranite_llm_ref
Smallest quant0.0 GB
Quick answer

granite vision crispembed needs about 2.7 GB of memory at Q4_K (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 5.9 GB (F16).

granite vision crispembed is a Granite model in GGUF format, quantized by cstr. The repository has 5 quant files, from 0.0 GB to 5.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
Q4_K2.0 GB 2.7 GB
Fits Get file →
Q8_03.4 GB 4.3 GB
Fits Get file →
F165.9 GB 7.1 GB
Fits Get file →

What GPU do you need for granite vision crispembed?

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 Q4_K (2.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.9 GB file, about 7.1 GB in use).

Which granite vision crispembed quant should you choose?

Q4_K (2.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite_llm_ref

Source

Quantized bycstr
FamilyGranite
Licenseapache-2.0
Downloads (HF)311
Last updated2026-08-02

Frequently asked questions about granite vision crispembed

How much VRAM does granite vision crispembed need?

About 2.7 GB at Q4_K with an 8K context window. That is the 2.0 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 crispembed on an 8 GB GPU?

Yes, with F16: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite vision crispembed GGUF?

It depends on the quant: file is 0.0 GB, file is 0.0 GB, Q4_K is 2.0 GB, Q8_0 is 3.4 GB, F16 is 5.9 GB.

Where can I download granite vision crispembed GGUF?

The files are on Hugging Face in the cstr/granite-vision-crispembed-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 crispembed 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.

Other GGUFs of granite-vision-3.3-2b

More from cstr

All by cstr →

More Granite models

All Granite →