GR

Mordant 3B Think

GraniteGGUF by KezmarkUpdated 2026-07-03
Download on Hugging Face
Parameters3.4B
Context128K
Layers40
Architecturegranite
Smallest quant2.8 GB
Quick answer

Mordant 3B Think 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 3 quants, from 2.8 GB (Q6_K) to 6.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Mordant 3B Think is a 3.4B-parameter Granite model in GGUF format, quantized by Kezmark. Its trained context length is 128K tokens. The repository has 3 quant files, from 2.8 GB (Q6_K) to 6.8 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K2.8 GB 4.0 GB
Fits Get file →
Q8_03.6 GB 4.8 GB
Fits Get file →
BF166.8 GB 8.0 GB
Tight Get file →

What GPU do you need for Mordant 3B Think?

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 Q6_K (2.8 GB file, about 4.0 GB in use).
  • 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 BF16 (6.8 GB file, about 8.0 GB in use).

Which Mordant 3B Think 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.

If memory is tight, the smallest file is Q6_K at 2.8 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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 byKezmark
FamilyGranite
Licenseapache-2.0
Downloads (HF)189
Last updated2026-07-03

Frequently asked questions about Mordant 3B Think

How much VRAM does Mordant 3B Think 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 Mordant 3B Think on an 8 GB GPU?

Yes, with BF16: 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 Mordant 3B Think GGUF?

It depends on the quant: Q6_K is 2.8 GB, Q8_0 is 3.6 GB, BF16 is 6.8 GB.

What context length does Mordant 3B Think 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 Mordant 3B Think GGUF?

The files are on Hugging Face in the Kezmark/Mordant-3B-Think repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mordant 3B Think 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 Kezmark

All by Kezmark →

More Granite models

All Granite →

Other tiny models

All tiny models →