Instructions to use ledgergap/Pollux-4B-Judge-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ledgergap/Pollux-4B-Judge-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ledgergap/Pollux-4B-Judge-GGUF",
	filename="Pollux-4B-Judge.BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ledgergap/Pollux-4B-Judge-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ledgergap/Pollux-4B-Judge-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf ledgergap/Pollux-4B-Judge-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ledgergap/Pollux-4B-Judge-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf ledgergap/Pollux-4B-Judge-GGUF:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ledgergap/Pollux-4B-Judge-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf ledgergap/Pollux-4B-Judge-GGUF:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ledgergap/Pollux-4B-Judge-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ledgergap/Pollux-4B-Judge-GGUF:BF16

Use Docker

docker model run hf.co/ledgergap/Pollux-4B-Judge-GGUF:BF16

LM Studio
Jan

vLLM

How to use ledgergap/Pollux-4B-Judge-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ledgergap/Pollux-4B-Judge-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ledgergap/Pollux-4B-Judge-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ledgergap/Pollux-4B-Judge-GGUF:BF16

Ollama
How to use ledgergap/Pollux-4B-Judge-GGUF with Ollama:
```
ollama run hf.co/ledgergap/Pollux-4B-Judge-GGUF:BF16
```

Unsloth Studio

How to use ledgergap/Pollux-4B-Judge-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ledgergap/Pollux-4B-Judge-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ledgergap/Pollux-4B-Judge-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ledgergap/Pollux-4B-Judge-GGUF to start chatting

How to use ledgergap/Pollux-4B-Judge-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ledgergap/Pollux-4B-Judge-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ledgergap/Pollux-4B-Judge-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ledgergap/Pollux-4B-Judge-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ledgergap/Pollux-4B-Judge-GGUF:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ledgergap/Pollux-4B-Judge-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ledgergap/Pollux-4B-Judge-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ledgergap/Pollux-4B-Judge-GGUF:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ledgergap/Pollux-4B-Judge-GGUF:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use ledgergap/Pollux-4B-Judge-GGUF with Docker Model Runner:
```
docker model run hf.co/ledgergap/Pollux-4B-Judge-GGUF:BF16
```

Lemonade

How to use ledgergap/Pollux-4B-Judge-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ledgergap/Pollux-4B-Judge-GGUF:BF16

Run and chat with the model

lemonade run user.Pollux-4B-Judge-GGUF-BF16

List all available models

lemonade list

Pollux-4B-Judge GGUF

This repository contains GGUF versions of ai-forever/Pollux-4B-Judge for local inference with llama.cpp, LM Studio, and other GGUF-compatible runtimes.

Pollux-4B-Judge is a Russian-oriented LLM-as-a-judge model based on Qwen3-4B. It is intended for evaluating model answers against a specific criterion and scoring rubric.

Files

File	Type	Quantized	Notes
`Pollux-4B-Judge.BF16.gguf`	BF16 GGUF conversion	No	High-precision reference version
`Pollux-4B-Judge.Q8_0.gguf`	Q8_0 GGUF quantization	Yes	High-quality quantized version

Which file should I use?

Use Pollux-4B-Judge.BF16.gguf if you want the highest-quality reference version.

Use Pollux-4B-Judge.Q8_0.gguf if you want a practical local version with lower memory usage and minimal expected quality loss.

Recommended inference settings

For judge-style usage, the original model card uses:

Setting	Value
Temperature	`0.0`
Max tokens	`512`

For local GGUF inference, choose a context length large enough to fit the full evaluation prompt: instruction, reference answer, evaluated answer, criterion, and rubric. A practical starting point is 8192, but this is a local runtime recommendation rather than an official value from the original model card.

The model is intended to evaluate one criterion per request.

Prompt format

Recommended prompt structure:

### Задание для оценки:
{instruction}

### Эталонный ответ:
{reference_answer}

### Ответ для оценки:
{answer}

### Критерий оценки:
{criterion}

### Шкала оценивания по критерию:
{rubric}

Use with llama.cpp

BF16:

llama-server -hf ledgergap/Pollux-4B-Judge-GGUF:BF16 -c 8192 -ngl 99

Q8_0:

llama-server -hf ledgergap/Pollux-4B-Judge-GGUF:Q8_0 -c 8192 -ngl 99

Use with LM Studio

Open LM Studio and paste this repository URL into the model search/download field:

https://huggingface.co/ledgergap/Pollux-4B-Judge-GGUF

Then select either the BF16 or Q8_0 GGUF file.

Original model

Original model: ai-forever/Pollux-4B-Judge

Downloads last month: 71

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

8-bit

16-bit

Model tree for ledgergap/Pollux-4B-Judge-GGUF

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

ai-forever/Pollux-4B-Judge

Quantized

(2)

this model