PO

polanka 3b pretrain full v0.4

PolankaGGUF by NikolayKozloffUpdated 2024-04-06
Download on Hugging Face
Parameters3.43B
Context2K
Layers26
Architecturellama
Smallest quant3.6 GB
Quick answer

polanka 3b pretrain full v0.4 needs about 6.9 GB of memory at Q8_0 (a 3.6 GB file) with an 8K context window, so it fits on a 8 GB GPU.

polanka 3b pretrain full v0.4 is a 3.43B-parameter Polanka model in GGUF format, quantized by NikolayKozloff. Its trained context length is 2K tokens. The repository has 1 quant file, from 3.6 GB (Q8_0) to 3.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.6 GB 4.8 GB
Fits Get file →

What GPU do you need for polanka 3b pretrain full v0.4?

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 Q8_0 (3.6 GB file, about 6.9 GB in use).

Which polanka 3b pretrain full v0.4 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.43B
Layers26
Trained context2,048 tokens
KV cache (fp16)325 KB per token

Source

Quantized byNikolayKozloff
FamilyPolanka
Licenseapache-2.0
Downloads (HF)28
Last updated2024-04-06

Frequently asked questions about polanka 3b pretrain full v0.4

How much VRAM does polanka 3b pretrain full v0.4 need?

About 6.9 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 polanka 3b pretrain full v0.4 on an 8 GB GPU?

Yes, with Q8_0: the 3.6 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of polanka 3b pretrain full v0.4 GGUF?

It depends on the quant: Q8_0 is 3.6 GB.

What context length does polanka 3b pretrain full v0.4 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download polanka 3b pretrain full v0.4 GGUF?

The files are on Hugging Face in the NikolayKozloff/polanka-3b-pretrain-full-v0.4-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 3b pretrain full v0.4 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 NikolayKozloff

All by NikolayKozloff →

More Polanka models

All Polanka →

Other tiny models

All tiny models →