GR

Granite 3.3 8b Instruct

GraniteGGUF by ZeroWwUpdated 2025-04-17
Download on Hugging Face
Parameters8.17B
Context128K
Layers40
Architecturegranite
Smallest quant5.0 GB
Quick answer

Granite 3.3 8b Instruct needs about 8.8 GB of memory at Q6_K (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 5.0 GB to 16.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Granite 3.3 8b Instruct is a 8.17B-parameter Granite model in GGUF format, quantized by ZeroWw. Its trained context length is 128K tokens. The repository has 6 quant files, from 5.0 GB to 16.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—5.0 GB 6.8 GB
Fits Get file →
Q5_K6.0 GB 7.9 GB
Tight Get file →
Q6_K6.9 GB 8.8 GB
Too big Get file →
—8.7 GB 10.5 GB
Too big Get file →
Q8_08.9 GB 10.7 GB
Too big Get file →
F1616.3 GB 18.2 GB
Too big Get file →

What GPU do you need for Granite 3.3 8b Instruct?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K (6.0 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.3 GB file, about 18.2 GB in use).

Which Granite 3.3 8b Instruct quant should you choose?

Q6_K (6.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is the first one in the table at 5.0 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
Parameters8.17B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byZeroWw
FamilyGranite
Licensemit
Downloads (HF)39
Last updated2025-04-17

Frequently asked questions about Granite 3.3 8b Instruct

How much VRAM does Granite 3.3 8b Instruct need?

About 8.8 GB at Q6_K with an 8K context window. That is the 6.9 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 8b Instruct on an 8 GB GPU?

Yes, with Q5_K: the 6.0 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 3.3 8b Instruct GGUF?

It depends on the quant: file is 5.0 GB, Q5_K is 6.0 GB, Q6_K is 6.9 GB, file is 8.7 GB, Q8_0 is 8.9 GB, F16 is 16.3 GB.

What context length does Granite 3.3 8b Instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Granite 3.3 8b Instruct GGUF?

The files are on Hugging Face in the ZeroWw/granite-3.3-8b-instruct-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 3.3 8b Instruct use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from ZeroWw

All by ZeroWw →

More Granite models

All Granite →

Other small models

All small models →