GR

ibm granite docling 258M

GraniteGGUF by danchevUpdated 2025-11-04
Download on Hugging Face
Parameters164M
Context8K
Layers30
Architecturellama
Smallest quant0.2 GB
Quick answer

ibm granite docling 258M needs about 1.0 GB of memory at BF16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.2 GB (Q8_0) to 0.3 GB (F16).

ibm granite docling 258M is a 164M-parameter Granite model in GGUF format, quantized by danchev. Its trained context length is 8K tokens. The repository has 3 quant files, from 0.2 GB (Q8_0) to 0.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.2 GB 0.9 GB
Fits Get file →
BF160.3 GB 1.0 GB
Fits Get file →
F160.3 GB 1.0 GB
Fits Get file →

What GPU do you need for ibm granite docling 258M?

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 BF16 (0.3 GB file, about 1.0 GB in use).

Which ibm granite docling 258M quant should you choose?

BF16 (0.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters164M
Layers30
Trained context8,192 tokens
KV cache (fp16)23 KB per token

Source

Quantized bydanchev
FamilyGranite
Licenseapache-2.0
Downloads (HF)109
Last updated2025-11-04

Frequently asked questions about ibm granite docling 258M

How much VRAM does ibm granite docling 258M need?

About 1.0 GB at BF16 with an 8K context window. That is the 0.3 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 ibm granite docling 258M on an 8 GB GPU?

Yes, with BF16: the 0.3 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ibm granite docling 258M GGUF?

It depends on the quant: Q8_0 is 0.2 GB, BF16 is 0.3 GB, F16 is 0.3 GB.

What context length does ibm granite docling 258M support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download ibm granite docling 258M GGUF?

The files are on Hugging Face in the danchev/ibm-granite-docling-258M-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 ibm granite docling 258M 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-docling-258M

Similar models

Browse all →

More from danchev

All by danchev →

More Granite models

All Granite →

Other tiny models

All tiny models →