GR

Granite Embedding

GraniteGGUF by arshvirUpdated 2026-08-18
Download on Hugging Face
Parameters312M
Context32K
Layers22
Architecturemodern-bert
Smallest quant0.6 GB
Quick answer

Granite Embedding needs about 1.7 GB of memory at F16 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.2 GB.

Granite Embedding is a 312M-parameter Granite model in GGUF format, quantized by arshvir. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.6 GB (F16) to 0.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.6 GB 1.7 GB
Fits Get file →

What GPU do you need for Granite Embedding?

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 F16 (0.6 GB file, about 1.7 GB in use).

Which Granite Embedding quant should you choose?

F16 (0.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemodern-bert
Parameters312M
Layers22
Trained context32,768 tokens
KV cache (fp16)66 KB per token

Source

Quantized byarshvir
FamilyGranite
Licenseapache-2.0
Downloads (HF)50
Last updated2026-08-18

Frequently asked questions about Granite Embedding

How much VRAM does Granite Embedding need?

About 1.7 GB at F16 with an 8K context window. That is the 0.6 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 Embedding on an 8 GB GPU?

Yes, with F16: the 0.6 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite Embedding GGUF?

It depends on the quant: F16 is 0.6 GB.

What context length does Granite Embedding support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.2 GB at 32K.

Where can I download Granite Embedding GGUF?

The files are on Hugging Face in the arshvir/granite-embedding-311m-multilingual-r2-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 Embedding 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-embedding-311m-multilingual-r2

Similar models

Browse all →

More from arshvir

All by arshvir →

More Granite models

All Granite →

Other tiny models

All tiny models →