PU

Pub

PubGGUF by LokosotoUpdated 2026-06-09
Download on Hugging Face
Parameters21B
Context—
Layers—
Architectureltxv
Smallest quant15.2 GB
Quick answer

Pub needs about 17.6 GB of memory at Q5_K_S (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.2 GB (Q5_K_S) to 22.8 GB (Q8_0).

Pub is a 21B-parameter Pub model in GGUF format, quantized by Lokosoto. The repository has 2 quant files, from 15.2 GB (Q5_K_S) to 22.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S15.2 GB 17.6 GB
Too big Get file →
Q8_022.8 GB 26.0 GB
Too big Get file →

What GPU do you need for Pub?

These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_K_S (15.2 GB file, about 17.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.8 GB file, about 26.0 GB in use).

Which Pub quant should you choose?

Q5_K_S (15.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureltxv
Parameters21B

Source

Quantized byLokosoto
FamilyPub
RepositoryLokosoto/Pub
Licenseother
Downloads (HF)3
Last updated2026-06-09

Frequently asked questions about Pub

How much VRAM does Pub need?

About 17.6 GB at Q5_K_S with an 8K context window. That is the 15.2 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 Pub on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Pub GGUF?

It depends on the quant: Q5_K_S is 15.2 GB, Q8_0 is 22.8 GB.

Where can I download Pub GGUF?

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

What license does Pub use?

Hugging Face lists the license as other. 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 →

Other medium models

All medium models →