PO

polanka 3.4b v0.3

PolankaGGUF by piotr-aiUpdated 2025-02-03
Download on Hugging Face
Parameters3.46B
Context32K
Layers44
Architectureqwen2
Smallest quant6.9 GB
Quick answer

polanka 3.4b v0.3 needs about 7.8 GB of memory at BF16 (a 6.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.5 GB.

polanka 3.4b v0.3 is a 3.46B-parameter Polanka model in GGUF format, quantized by piotr-ai. Its trained context length is 32K tokens. The repository has 1 quant file, from 6.9 GB (BF16) to 6.9 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF166.9 GB 7.8 GB
Tight Get file →

What GPU do you need for polanka 3.4b v0.3?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is BF16 (6.9 GB file, about 7.8 GB in use).

Which polanka 3.4b v0.3 quant should you choose?

BF16 (6.9 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters3.46B
Layers44
Trained context32,768 tokens
KV cache (fp16)44 KB per token

Source

Quantized bypiotr-ai
FamilyPolanka
Licenseapache-2.0
Downloads (HF)7
Last updated2025-02-03

Frequently asked questions about polanka 3.4b v0.3

How much VRAM does polanka 3.4b v0.3 need?

About 7.8 GB at BF16 with an 8K context window. That is the 6.9 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 polanka 3.4b v0.3 on an 8 GB GPU?

Yes, with BF16: the 6.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of polanka 3.4b v0.3 GGUF?

It depends on the quant: BF16 is 6.9 GB.

What context length does polanka 3.4b v0.3 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.5 GB at 32K.

Where can I download polanka 3.4b v0.3 GGUF?

The files are on Hugging Face in the piotr-ai/polanka__3.4b__v0.3__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 3.4b v0.3 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 tiny models

All tiny models →