GR

Kestrel 4.1 3b Final

GraniteGGUF by felixreverettUpdated 2026-10-12
Download on Hugging Face
Parameters3.4B
Context128K
Layers40
Architecturegranite
Smallest quant2.1 GB
Quick answer

Kestrel 4.1 3b Final needs about 3.3 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 2.1 GB (Q4_K_M) to 16.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Kestrel 4.1 3b Final is a 3.4B-parameter Granite model in GGUF format, quantized by felixreverett. Its trained context length is 128K tokens. The repository has 8 quant files, from 2.1 GB (Q4_K_M) to 16.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.1 GB 3.3 GB
Fits Get file →
Q4_K_M2.1 GB 3.3 GB
Fits Get file →
Q4_K_M5.1 GB 6.3 GB
Fits Get file →
Q4_K_M5.1 GB 6.3 GB
Fits Get file →
F166.8 GB 8.0 GB
Tight Get file →
F166.8 GB 8.0 GB
Tight Get file →
F1616.8 GB 17.9 GB
Too big Get file →
F1616.8 GB 17.9 GB
Too big Get file →

What GPU do you need for Kestrel 4.1 3b Final?

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 Q4_K_M (2.1 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.1 GB file, about 3.3 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (6.8 GB file, about 8.0 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (6.8 GB file, about 8.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.8 GB file, about 17.9 GB in use).

Which Kestrel 4.1 3b Final quant should you choose?

Q4_K_M is the usual starting point for Kestrel 4.1 3b Final: it balances file size and quality well. Here it is a 2.1 GB file.

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 byfelixreverett
FamilyGranite
Licensemit
Downloads (HF)70
Last updated2026-10-12

Frequently asked questions about Kestrel 4.1 3b Final

How much VRAM does Kestrel 4.1 3b Final need?

About 3.3 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Kestrel 4.1 3b Final 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 Kestrel 4.1 3b Final GGUF?

It depends on the quant: Q4_K_M is 2.1 GB, Q4_K_M is 2.1 GB, Q4_K_M is 5.1 GB, Q4_K_M is 5.1 GB, F16 is 6.8 GB, F16 is 6.8 GB and 2 more.

What context length does Kestrel 4.1 3b Final 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 Kestrel 4.1 3b Final GGUF?

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

What license does Kestrel 4.1 3b Final 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.

Other GGUFs of granite-4.1-3b

Similar models

Browse all →

More Granite models

All Granite →

Other tiny models

All tiny models →