KU

Kumru 2B v0.2.1

KumruGGUF by icecubetrUpdated 2025-10-15
Download on Hugging Face
Parameters2.38B
Context8K
Layers18
Architecturellama
Smallest quant0.7 GB
Quick answer

Kumru 2B v0.2.1 needs about 2.3 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 0.7 GB (IQ2_XXS) to 4.8 GB (F16).

Kumru 2B v0.2.1 is a 2.38B-parameter Kumru model in GGUF format, quantized by icecubetr. Its trained context length is 8K tokens. The repository has 9 quant files, from 0.7 GB (IQ2_XXS) to 4.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS0.7 GB 1.5 GB
Fits Get file →
Q2_K0.9 GB 1.7 GB
Fits Get file →
Q3_K_M1.2 GB 2.0 GB
Fits Get file →
IQ4_XS1.3 GB 2.1 GB
Fits Get file →
Q4_K_S1.4 GB 2.2 GB
Fits Get file →
Q4_K_M1.5 GB 2.3 GB
Fits Get file →
Q6_K2.0 GB 2.8 GB
Fits Get file →
Q8_02.5 GB 3.3 GB
Fits Get file →
F164.8 GB 5.6 GB
Fits Get file →

What GPU do you need for Kumru 2B v0.2.1?

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 Q8_0 (2.5 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (4.8 GB file, about 5.6 GB in use).

Which Kumru 2B v0.2.1 quant should you choose?

Q4_K_M is the usual starting point for Kumru 2B v0.2.1: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 2.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_XXS at 0.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.38B
Layers18
Trained context8,192 tokens
KV cache (fp16)36 KB per token

Source

Quantized byicecubetr
FamilyKumru
Licenseapache-2.0
Downloads (HF)345
Last updated2025-10-15

Frequently asked questions about Kumru 2B v0.2.1

How much VRAM does Kumru 2B v0.2.1 need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.5 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 Kumru 2B v0.2.1 on an 8 GB GPU?

Yes, with F16: the 4.8 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kumru 2B v0.2.1 GGUF?

It depends on the quant: IQ2_XXS is 0.7 GB, Q2_K is 0.9 GB, Q3_K_M is 1.2 GB, IQ4_XS is 1.3 GB, Q4_K_S is 1.4 GB, Q4_K_M is 1.5 GB and 3 more.

What context length does Kumru 2B v0.2.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.

Where can I download Kumru 2B v0.2.1 GGUF?

The files are on Hugging Face in the icecubetr/Kumru-2B-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 Kumru 2B v0.2.1 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 Kumru-2B

Similar models

Browse all →

More from icecubetr

All by icecubetr →

More Kumru models

All Kumru →

Other tiny models

All tiny models →