GR

granite 4 h 3b unsloth fft

GraniteGGUF by sjpritchardUpdated 2026-01-01
Download on Hugging Face
Parameters3.19B
Context1024K
Layers40
Architecturegranitehybrid
Smallest quant1.9 GB
Quick answer

granite 4 h 3b unsloth fft needs about 5.1 GB of memory at Q4_K_M (a 1.9 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 10.7 GB.

granite 4 h 3b unsloth fft is a 3.19B-parameter Granite model in GGUF format, quantized by sjpritchard. Its trained context length is 1024K tokens. The repository has 1 quant file, from 1.9 GB (Q4_K_M) to 1.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.9 GB 5.1 GB
Fits Get file →

What GPU do you need for granite 4 h 3b unsloth fft?

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 (1.9 GB file, about 5.1 GB in use).

Which granite 4 h 3b unsloth fft quant should you choose?

Q4_K_M is the usual starting point for granite 4 h 3b unsloth fft: it balances file size and quality well. Here it is a 1.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranitehybrid
Parameters3.19B
Layers40
Trained context1,048,576 tokens
KV cache (fp16)320 KB per token

Source

Quantized bysjpritchard
FamilyGranite
Downloads (HF)12
Last updated2026-01-01

Frequently asked questions about granite 4 h 3b unsloth fft

How much VRAM does granite 4 h 3b unsloth fft need?

About 5.1 GB at Q4_K_M with an 8K context window. That is the 1.9 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 4 h 3b unsloth fft on an 8 GB GPU?

Yes, with Q4_K_M: the 1.9 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite 4 h 3b unsloth fft GGUF?

It depends on the quant: Q4_K_M is 1.9 GB.

What context length does granite 4 h 3b unsloth fft 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 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download granite 4 h 3b unsloth fft GGUF?

The files are on Hugging Face in the sjpritchard/granite_4_h_3b_unsloth_fft_gguf 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 Granite models

All Granite →

Other tiny models

All tiny models →