GR

granite 3.1 8b finetuned

GraniteGGUF by raznaeeUpdated 2025-10-28
Download on Hugging Face
Parameters8.17B
Context128K
Layers40
Architecturegranite
Smallest quant16.3 GB
Quick answer

granite 3.1 8b finetuned needs about 18.2 GB of memory at its main file (a 16.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

granite 3.1 8b finetuned is a 8.17B-parameter Granite model in GGUF format, quantized by raznaee. Its trained context length is 128K tokens. The repository has 1 quant file, from 16.3 GB to 16.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—16.3 GB 18.2 GB
Too big Get file →

What GPU do you need for granite 3.1 8b finetuned?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is the main file (16.3 GB file, about 18.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters8.17B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byraznaee
FamilyGranite
Downloads (HF)8
Last updated2025-10-28

Frequently asked questions about granite 3.1 8b finetuned

How much VRAM does granite 3.1 8b finetuned need?

About 18.2 GB at its main file with an 8K context window. That is the 16.3 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 granite 3.1 8b finetuned on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of granite 3.1 8b finetuned GGUF?

It depends on the quant: file is 16.3 GB.

What context length does granite 3.1 8b finetuned 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 3.1 8b finetuned GGUF?

The files are on Hugging Face in the raznaee/granite-3.1-8b-finetuned repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from raznaee

All by raznaee →

More Granite models

All Granite →

Other small models

All small models →