PO

polanka 3.6b exp WIP 251227

PolankaGGUF by piotr-aiUpdated 2025-12-27
Download on Hugging Face
Parameters3.67B
Context40K
Layers40
Architectureqwen3moe
Smallest quant2.8 GB
Quick answer

polanka 3.6b exp WIP 251227 needs about 5.1 GB of memory at its main file (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.8 GB to 3.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

polanka 3.6b exp WIP 251227 is a 3.67B-parameter Polanka model in GGUF format, quantized by piotr-ai. Its trained context length is 40K tokens. The repository has 3 quant files, from 2.8 GB to 3.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.8 GB 4.6 GB
Fits Get file →
—3.2 GB 5.1 GB
Fits Get file →
—3.9 GB 5.8 GB
Fits Get file →

What GPU do you need for polanka 3.6b exp WIP 251227?

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 (3.9 GB file, about 5.8 GB in use).

Which polanka 3.6b exp WIP 251227 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 2.8 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters3.67B (approximate, mixture of experts)
Layers40
Trained context40,960 tokens
KV cache (fp16)160 KB per token

Source

Quantized bypiotr-ai
FamilyPolanka
Licenseapache-2.0
Downloads (HF)44
Last updated2025-12-27

Frequently asked questions about polanka 3.6b exp WIP 251227

How much VRAM does polanka 3.6b exp WIP 251227 need?

About 5.1 GB at its main file with an 8K context window. That is the 3.2 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 polanka 3.6b exp WIP 251227 on an 8 GB GPU?

Yes, with the smaller files: the 3.9 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of polanka 3.6b exp WIP 251227 GGUF?

It depends on the quant: file is 2.8 GB, file is 3.2 GB, file is 3.9 GB.

What context length does polanka 3.6b exp WIP 251227 support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download polanka 3.6b exp WIP 251227 GGUF?

The files are on Hugging Face in the piotr-ai/polanka_3.6b_exp_WIP_251227_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 polanka 3.6b exp WIP 251227 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.

Similar models

Browse all →

More from piotr-ai

All by piotr-ai →

More Polanka models

All Polanka →

Other small models

All small models →