GR

ToastyPigeon granite 3.3 8b creative

GraniteGGUF by ArtusDevUpdated 2025-04-18
Download on Hugging Face
Parameters8.17B
Context128K
Layers40
Architecturegranite
Smallest quant5.6 GB
Quick answer

ToastyPigeon granite 3.3 8b creative needs about 7.6 GB of memory at Q5_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.6 GB (Q5_K_S) to 8.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

ToastyPigeon granite 3.3 8b creative is a 8.17B-parameter Granite model in GGUF format, quantized by ArtusDev. Its trained context length is 128K tokens. The repository has 4 quant files, from 5.6 GB (Q5_K_S) to 8.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S5.6 GB 7.5 GB
Tight Get file →
Q5_K_M5.8 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.5 GB
Too big Get file →
Q8_08.7 GB 10.5 GB
Too big Get file →

What GPU do you need for ToastyPigeon granite 3.3 8b creative?

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_M (5.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.5 GB in use).

Which ToastyPigeon granite 3.3 8b creative quant should you choose?

Q5_K_M (5.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q5_K_S at 5.6 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 byArtusDev
FamilyGranite
Licenseapache-2.0
Downloads (HF)38
Last updated2025-04-18

Frequently asked questions about ToastyPigeon granite 3.3 8b creative

How much VRAM does ToastyPigeon granite 3.3 8b creative need?

About 7.6 GB at Q5_K_M with an 8K context window. That is the 5.8 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 ToastyPigeon granite 3.3 8b creative on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ToastyPigeon granite 3.3 8b creative GGUF?

It depends on the quant: Q5_K_S is 5.6 GB, Q5_K_M is 5.8 GB, Q6_K is 6.7 GB, Q8_0 is 8.7 GB.

What context length does ToastyPigeon granite 3.3 8b creative 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 ToastyPigeon granite 3.3 8b creative GGUF?

The files are on Hugging Face in the ArtusDev/ToastyPigeon_granite-3.3-8b-creative-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 ToastyPigeon granite 3.3 8b creative 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-3.3-8b-creative

Similar models

Browse all →

More from ArtusDev

All by ArtusDev →

More Granite models

All Granite →

Other small models

All small models →