GR

fine tuned granite 4 h 1b

GraniteGGUF by raznaeeUpdated 2025-11-08
Download on Hugging Face
Parameters1.46B
Context1024K
Layers40
Architecturegranitehybrid
Smallest quant2.9 GB
Quick answer

fine tuned granite 4 h 1b needs about 5.4 GB of memory at its main file (a 2.9 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 8.1 GB.

fine tuned granite 4 h 1b is a 1.46B-parameter Granite model in GGUF format, quantized by raznaee. Its trained context length is 1024K tokens. The repository has 1 quant file, from 2.9 GB to 2.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.9 GB 5.4 GB
Fits Get file →

What GPU do you need for fine tuned granite 4 h 1b?

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 the main file (2.9 GB file, about 5.4 GB in use).

Specifications

Architecture from the GGUF header

Architecturegranitehybrid
Parameters1.46B
Layers40
Trained context1,048,576 tokens
KV cache (fp16)240 KB per token

Source

Quantized byraznaee
FamilyGranite
Downloads (HF)7
Last updated2025-11-08

Frequently asked questions about fine tuned granite 4 h 1b

How much VRAM does fine tuned granite 4 h 1b need?

About 5.4 GB at its main file with an 8K context window. That is the 2.9 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 fine tuned granite 4 h 1b on an 8 GB GPU?

Yes, with the smaller files: the 2.9 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of fine tuned granite 4 h 1b GGUF?

It depends on the quant: file is 2.9 GB.

What context length does fine tuned granite 4 h 1b support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download fine tuned granite 4 h 1b GGUF?

The files are on Hugging Face in the raznaee/fine-tuned-granite-4-h-1b 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 tiny models

All tiny models →