Instructions to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="prithivMLmods/Polaris-4B-Preview-F32-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Polaris-4B-Preview-F32-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/Polaris-4B-Preview-F32-GGUF",
	filename="Polaris-4B-Preview.BF16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/Polaris-4B-Preview-F32-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 prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M

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 prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M

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 prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Polaris-4B-Preview-F32-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Polaris-4B-Preview-F32-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/Polaris-4B-Preview-F32-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Polaris-4B-Preview-F32-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/Polaris-4B-Preview-F32-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Polaris-4B-Preview-F32-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M
```

Unsloth Studio

How to use prithivMLmods/Polaris-4B-Preview-F32-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 prithivMLmods/Polaris-4B-Preview-F32-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 prithivMLmods/Polaris-4B-Preview-F32-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/Polaris-4B-Preview-F32-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/Polaris-4B-Preview-F32-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Polaris-4B-Preview-F32-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Polaris-4B-Preview-F32-GGUF-Q4_K_M

List all available models

lemonade list

Polaris-4B-Preview-F32-GGUF

Polaris is an open-source post-training method that uses reinforcement learning (RL) scaling to refine and enhance models with advanced reasoning abilities. Our research shows that even top-tier models like Qwen3-4B can achieve significant improvements on challenging reasoning tasks when optimized with Polaris. By leveraging open-source data and academic-level resources, Polaris pushes the capabilities of open-recipe reasoning models to unprecedented heights. In benchmark tests, our method even surpasses top commercial systems, including Claude-4-Opus, Grok-3-Beta, and o3-mini-high .

Model Files

File Name	Size	Format	Description
Polaris-4B-Preview.F32.gguf	16.1 GB	F32	Full precision 32-bit floating point
Polaris-4B-Preview.F16.gguf	8.05 GB	F16	Half precision 16-bit floating point
Polaris-4B-Preview.BF16.gguf	8.05 GB	BF16	Brain floating point 16-bit
Polaris-4B-Preview.Q8_0.gguf	4.28 GB	Q8_0	8-bit quantized
Polaris-4B-Preview.Q6_K.gguf	3.31 GB	Q6_K	6-bit quantized
Polaris-4B-Preview.Q5_K_M.gguf	2.89 GB	Q5_K_M	5-bit quantized, medium quality
Polaris-4B-Preview.Q5_K_S.gguf	2.82 GB	Q5_K_S	5-bit quantized, small quality
Polaris-4B-Preview.Q4_K_M.gguf	2.5 GB	Q4_K_M	4-bit quantized, medium quality
Polaris-4B-Preview.Q4_K_S.gguf	2.38 GB	Q4_K_S	4-bit quantized, small quality
Polaris-4B-Preview.Q3_K_L.gguf	2.24 GB	Q3_K_L	3-bit quantized, large quality
Polaris-4B-Preview.Q3_K_M.gguf	2.08 GB	Q3_K_M	3-bit quantized, medium quality
Polaris-4B-Preview.Q3_K_S.gguf	1.89 GB	Q3_K_S	3-bit quantized, small quality
Polaris-4B-Preview.Q2_K.gguf	1.67 GB	Q2_K	2-bit quantized

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

Downloads last month: 95

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Model tree for prithivMLmods/Polaris-4B-Preview-F32-GGUF

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

POLARIS-Project/Polaris-4B-Preview

Quantized

(14)

this model