GR

ha voice granite 3b

GraniteGGUF by infohoundUpdated 2026-07-30
Download on Hugging Face
Parameters3.4B
Context128K
Layers40
Architecturegranite
Smallest quant3.6 GB
Quick answer

ha voice granite 3b needs about 4.8 GB of memory at Q8_0 (a 3.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.6 GB (Q8_0) to 6.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

ha voice granite 3b is a 3.4B-parameter Granite model in GGUF format, quantized by infohound. Its trained context length is 128K tokens. The repository has 2 quant files, from 3.6 GB (Q8_0) to 6.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.6 GB 4.8 GB
Fits Get file →
F166.8 GB 8.0 GB
Tight Get file →

What GPU do you need for ha voice granite 3b?

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 Q8_0 (3.6 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.8 GB file, about 8.0 GB in use).

Which ha voice granite 3b quant should you choose?

Q8_0 (3.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters3.4B
Layers40
Trained context131,072 tokens
KV cache (fp16)80 KB per token

Source

Quantized byinfohound
FamilyGranite
Licenseapache-2.0
Downloads (HF)539
Last updated2026-07-30

Frequently asked questions about ha voice granite 3b

How much VRAM does ha voice granite 3b need?

About 4.8 GB at Q8_0 with an 8K context window. That is the 3.6 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 ha voice granite 3b on an 8 GB GPU?

Yes, with F16: the 6.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ha voice granite 3b GGUF?

It depends on the quant: Q8_0 is 3.6 GB, F16 is 6.8 GB.

What context length does ha voice granite 3b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download ha voice granite 3b GGUF?

The files are on Hugging Face in the infohound/ha-voice-granite-3b-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 ha voice granite 3b 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-4.1-3b

Similar models

Browse all →

More from infohound

All by infohound →

More Granite models

All Granite →

Other tiny models

All tiny models →