GR

Granite 3.0 3b A800M Instruct

GraniteGGUF by FelladrinUpdated 2024-10-26
Download on Hugging Face
Parameters3.37B
Context4K
Layers32
Architecturegranitemoe
Smallest quant2.5 GB
Quick answer

Granite 3.0 3b A800M Instruct needs about 3.5 GB of memory at its main file (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Granite 3.0 3b A800M Instruct is a 3.37B-parameter Granite model in GGUF format, quantized by Felladrin. Its trained context length is 4K tokens. The repository has 1 quant file, from 2.5 GB to 2.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.5 GB (34 parts) 3.2 GB
Fits Get file →

What GPU do you need for Granite 3.0 3b A800M 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: the best quant that fits is the main file (2.5 GB file, about 3.5 GB in use).

Specifications

Architecture from the GGUF header

Architecturegranitemoe
Parameters3.37B (approximate, mixture of experts)
Layers32
Trained context4,096 tokens
KV cache (fp16)64 KB per token

Source

Quantized byFelladrin
FamilyGranite
Licenseapache-2.0
Downloads (HF)3
Last updated2024-10-26

Frequently asked questions about Granite 3.0 3b A800M Instruct

How much VRAM does Granite 3.0 3b A800M Instruct need?

About 3.5 GB at its main file with an 8K context window. That is the 2.5 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 3.0 3b A800M Instruct on an 8 GB GPU?

Yes, with the smaller files: the 2.5 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 3.0 3b A800M Instruct GGUF?

It depends on the quant: file is 2.5 GB.

What context length does Granite 3.0 3b A800M Instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.3 GB at 4K.

Where can I download Granite 3.0 3b A800M Instruct GGUF?

The files are on Hugging Face in the Felladrin/gguf-sharded-Q5_K_L-granite-3.0-3b-a800m-instruct 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 3.0 3b A800M Instruct 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-3.0-3b-a800m-instruct-GGUF

Similar models

Browse all →

More from Felladrin

All by Felladrin →

More Granite models

All Granite →

Other tiny models

All tiny models →