GR

Granite 3.1 8b Instruct R241212A

GraniteGGUF by RedHatAIUpdated 2024-12-17
Download on Hugging Face
Parameters8.17B
Context128K
Layers40
Architecturegranite
Smallest quant4.9 GB
Quick answer

Granite 3.1 8b Instruct R241212A needs about 6.8 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Granite 3.1 8b Instruct R241212A is a 8.17B-parameter Granite model in GGUF format, quantized by RedHatAI. Its trained context length is 128K tokens. The repository has 1 quant file, from 4.9 GB (Q4_K_M) to 4.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.8 GB
Fits Get file →

What GPU do you need for Granite 3.1 8b Instruct R241212A?

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 Q4_K_M (4.9 GB file, about 6.8 GB in use).

Which Granite 3.1 8b Instruct R241212A quant should you choose?

Q4_K_M is the usual starting point for Granite 3.1 8b Instruct R241212A: it balances file size and quality well. Here it is a 4.9 GB file.

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 byRedHatAI
FamilyGranite
Licenseapache-2.0
Downloads (HF)40
Last updated2024-12-17

Frequently asked questions about Granite 3.1 8b Instruct R241212A

How much VRAM does Granite 3.1 8b Instruct R241212A need?

About 6.8 GB at Q4_K_M with an 8K context window. That is the 4.9 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 3.1 8b Instruct R241212A on an 8 GB GPU?

Yes, with Q4_K_M: the 4.9 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 3.1 8b Instruct R241212A GGUF?

It depends on the quant: Q4_K_M is 4.9 GB.

What context length does Granite 3.1 8b Instruct R241212A 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 Instruct R241212A GGUF?

The files are on Hugging Face in the RedHatAI/granite-3.1-8b-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 3.1 8b Instruct R241212A 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.

Similar models

Browse all →

More from RedHatAI

All by RedHatAI →

More Granite models

All Granite →

Other small models

All small models →