PO

Pollux 4B Judge

PolluxGGUF by ledgergapUpdated 2026-06-08
Download on Hugging Face
Parameters4.02B
Context40K
Layers36
Architectureqwen3
Smallest quant4.3 GB
Quick answer

Pollux 4B Judge needs about 6.0 GB of memory at Q8_0 (a 4.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.3 GB (Q8_0) to 8.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Pollux 4B Judge is a 4.02B-parameter Pollux model in GGUF format, quantized by ledgergap. Its trained context length is 40K tokens. The repository has 2 quant files, from 4.3 GB (Q8_0) to 8.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.3 GB 6.0 GB
Fits Get file →
BF168.1 GB 9.8 GB
Too big Get file →

What GPU do you need for Pollux 4B Judge?

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 Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).

Which Pollux 4B Judge quant should you choose?

Q8_0 (4.3 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

Architectureqwen3
Parameters4.02B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized byledgergap
FamilyPollux
Licensemit
Downloads (HF)67
Last updated2026-06-08

Frequently asked questions about Pollux 4B Judge

How much VRAM does Pollux 4B Judge need?

About 6.0 GB at Q8_0 with an 8K context window. That is the 4.3 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 Pollux 4B Judge on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pollux 4B Judge GGUF?

It depends on the quant: Q8_0 is 4.3 GB, BF16 is 8.1 GB.

What context length does Pollux 4B Judge support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Pollux 4B Judge GGUF?

The files are on Hugging Face in the ledgergap/Pollux-4B-Judge-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 Pollux 4B Judge use?

Hugging Face lists the license as mit. 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 Pollux models

All Pollux →

Other small models

All small models →