Instructions to use vilarin/Llama-Qwen3-4B-RPG-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use vilarin/Llama-Qwen3-4B-RPG-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 vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vilarin/Llama-Qwen3-4B-RPG-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 vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vilarin/Llama-Qwen3-4B-RPG-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 vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vilarin/Llama-Qwen3-4B-RPG-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 vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M

Use Docker

docker model run hf.co/vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use vilarin/Llama-Qwen3-4B-RPG-gguf with Ollama:
```
ollama run hf.co/vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M
```

Unsloth Studio

How to use vilarin/Llama-Qwen3-4B-RPG-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 vilarin/Llama-Qwen3-4B-RPG-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 vilarin/Llama-Qwen3-4B-RPG-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vilarin/Llama-Qwen3-4B-RPG-gguf to start chatting

How to use vilarin/Llama-Qwen3-4B-RPG-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M

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": "vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use vilarin/Llama-Qwen3-4B-RPG-gguf with Docker Model Runner:
```
docker model run hf.co/vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M
```

Lemonade

How to use vilarin/Llama-Qwen3-4B-RPG-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Llama-Qwen3-4B-RPG-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use vilarin/Llama-Qwen3-4B-RPG-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 vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M

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 vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use vilarin/Llama-Qwen3-4B-RPG-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M

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 "vilarin/Llama-Qwen3-4B-RPG-gguf:Q4_K_M" \
  --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"

Llama-qwen3-4b-RPG

Llama-qwen3-4b-RPG is a fine-tuned variant of Qwen3-4B with facebook/research-plan-gen datasets Llama4-maverick generated, optimized for Research Plan Generation (RPG).
The model is designed to generate structured, high-quality research plans for complex scientific and technical tasks across multiple domains.

It is trained by using Unsloth notebook

Key Features

Research-aware generation
Produces clear, structured research plans with goals, methodologies, evaluation criteria, and constraints.
Two-stage training
- SFT warm-up for instruction following
- GRPO refinement using custom reward functions
Multi-domain coverage
- Machine Learning
- ArXiv research
- PubMed / biomedical research
Custom chat template Tailored specifically for research-planning tasks rather than generic chat.
Long-form optimized Tuned for long context windows and coherent multi-section outputs.

Training Overview

Base Model

Qwen3-4B

Dataset

Research Plan Generation Dataset
- Source: facebook/research-plan-gen
- Structure:
  - Goal
  - Rubric
  - Reference Solution

Training Strategy

Stage 1: Supervised Fine-Tuning (SFT)
- Learns structured research-plan formatting
- Aligns outputs with rubric-based expectations
Stage 2: GRPO Reinforcement Learning
- Improves plan quality using reward functions
- Encourages:
  - Completeness
  - Logical structure
  - Methodological rigor
  - Faithfulness to constraints

Intended Use Cases

Automated research planning
Scientific assistant systems
Academic proposal drafting
R&D ideation and experiment design
LLM-based research agents

Limitations

Not intended for factual verification or citation generation
Outputs should be reviewed by domain experts
Optimized for planning, not final paper writing

License

This model follows the license of its base model Qwen3-4B and the dataset used for training.
Please review upstream licenses before commercial use.

Acknowledgements

Qwen model family
Facebook Research Plan Generation dataset
Open-source RLHF / GRPO tooling

Citation

If you use this model in research or products, please cite appropriately.

Downloads last month: 21

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vilarin/Llama-Qwen3-4B-RPG-gguf

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

unsloth/Qwen3-4B-GGUF

Quantized

(3)

this model

vilarin
/

Llama-Qwen3-4B-RPG-gguf

Llama-qwen3-4b-RPG

Key Features

Training Overview

Base Model

Dataset

Training Strategy

Intended Use Cases

Limitations

License

Acknowledgements

Citation

Model tree for vilarin/Llama-Qwen3-4B-RPG-gguf

Dataset used to train vilarin/Llama-Qwen3-4B-RPG-gguf