GR

nani

GraniteGGUF by leeroy-jankinsUpdated 2026-08-27
Download on Hugging Face
Parameters1.63B
Context128K
Layers40
Architecturegranite
Smallest quant1.0 GB
Quick answer

nani needs about 4.2 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

nani is a 1.63B-parameter Granite model in GGUF format, quantized by leeroy-jankins. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.0 GB (Q4_K_M) to 1.0 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.0 GB 4.2 GB
Fits Get file →

What GPU do you need for nani?

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: the best quant that fits is Q4_K_M (1.0 GB file, about 4.2 GB in use).

Which nani quant should you choose?

Q4_K_M is the usual starting point for nani: it balances file size and quality well. Here it is a 1.0 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters1.63B
Layers40
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byleeroy-jankins
FamilyGranite
Licensemit
Downloads (HF)24
Last updated2026-08-27

Frequently asked questions about nani

How much VRAM does nani need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.0 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 nani on an 8 GB GPU?

Yes, with Q4_K_M: the 1.0 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of nani GGUF?

It depends on the quant: Q4_K_M is 1.0 GB.

What context length does nani support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download nani GGUF?

The files are on Hugging Face in the leeroy-jankins/nani repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does nani 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 leeroy-jankins

All by leeroy-jankins →

More Granite models

All Granite →

Other tiny models

All tiny models →