GR

Granite 3.3 2B Instruct Power

GraniteGGUF by librepoweraiUpdated 2026-06-12
Download on Hugging Face
Parameters2.53B
Context128K
Layers—
Architecturegranite
Smallest quant1.5 GB
Quick answer

Granite 3.3 2B Instruct Power needs about 2.2 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.5 GB (Q4_K_M) to 1.5 GB (Q4_K_M).

Granite 3.3 2B Instruct Power is a 2.53B-parameter Granite model in GGUF format, quantized by librepowerai. Its trained context length is 128K tokens. The repository has 2 quant files, from 1.5 GB (Q4_K_M) to 1.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.5 GB 2.2 GB
Fits Get file →
Q4_K_M1.5 GB 2.2 GB
Fits Get file →

What GPU do you need for Granite 3.3 2B Instruct Power?

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_M (1.5 GB file, about 2.2 GB in use).

Which Granite 3.3 2B Instruct Power quant should you choose?

Q4_K_M is the usual starting point for Granite 3.3 2B Instruct Power: it balances file size and quality well. Here it is a 1.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters2.53B
Trained context131,072 tokens

Source

Quantized bylibrepowerai
FamilyGranite
Licenseapache-2.0
Downloads (HF)60
Last updated2026-06-12

Frequently asked questions about Granite 3.3 2B Instruct Power

How much VRAM does Granite 3.3 2B Instruct Power need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.5 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 3.3 2B Instruct Power on an 8 GB GPU?

Yes, with Q4_K_M: the 1.5 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 3.3 2B Instruct Power GGUF?

It depends on the quant: Q4_K_M is 1.5 GB, Q4_K_M is 1.5 GB.

What context length does Granite 3.3 2B Instruct Power support?

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

Where can I download Granite 3.3 2B Instruct Power GGUF?

The files are on Hugging Face in the librepowerai/Granite-3.3-2B-Instruct-Power 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 3.3 2B Instruct Power 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-3.3-2b-instruct

Similar models

Browse all →

More from librepowerai

All by librepowerai →

More Granite models

All Granite →

Other tiny models

All tiny models →