Instructions to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF",
	filename=" GRAM-Qwen3-4B-RewardModel.BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-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/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-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/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M
```

Unsloth Studio new

How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-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/GRAM-Qwen3-4B-RewardModel-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/GRAM-Qwen3-4B-RewardModel-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/GRAM-Qwen3-4B-RewardModel-GGUF to start chatting

Pi new

How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-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": "prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/GRAM-Qwen3-4B-RewardModel-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 prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/GRAM-Qwen3-4B-RewardModel-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GRAM-Qwen3-4B-RewardModel-GGUF-Q4_K_M

List all available models

lemonade list

GRAM-Qwen3-4B-RewardModel-GGUF

GRAM-Qwen3-4B-RewardModel is a generative reward model developed to address reward generalization for Large Language Models (LLMs), released by NiuTrans. Unlike traditional models that depend heavily on task-specific labeled data, this model leverages both labeled and unlabeled data—a novel approach that allows it to generalize better across various tasks. It introduces a generative reward model framework that pre-trains on large amounts of unlabeled data and is subsequently fine-tuned with supervised data. The methodology also employs label smoothing and a regularized ranking loss to further boost performance, effectively bridging the gap between generative and discriminative reward modeling techniques.

This model is built on the Qwen3-4B base and can be directly used or adapted for aligning LLMs without the need to train a reward model from scratch on extensive datasets. In evaluations on the JudgeBench benchmark—covering Chat, Code, Math, and Safety tasks—GRAM-Qwen3-4B-RewardModel achieves a competitive average score of 65.9, making it suitable for use as an open-source, plug-and-play reward model for a variety of LLM alignment scenarios. The repository provides usage instructions and demonstration code to facilitate immediate adoption for research and development purposes

Model Files

Model File name	Size	QuantType
GRAM-Qwen3-4B-RewardModel.BF16.gguf	8.05 GB	BF16
GRAM-Qwen3-4B-RewardModel.F16.gguf	8.05 GB	F16
GRAM-Qwen3-4B-RewardModel.F32.gguf	16.1 GB	F32
GRAM-Qwen3-4B-RewardModel.Q2_K.gguf	1.67 GB	Q2_K
GRAM-Qwen3-4B-RewardModel.Q3_K_L.gguf	2.24 GB	Q3_K_L
GRAM-Qwen3-4B-RewardModel.Q3_K_M.gguf	2.08 GB	Q3_K_M
GRAM-Qwen3-4B-RewardModel.Q3_K_S.gguf	1.89 GB	Q3_K_S
GRAM-Qwen3-4B-RewardModel.Q4_K_M.gguf	2.5 GB	Q4_K_M
GRAM-Qwen3-4B-RewardModel.Q4_K_S.gguf	2.38 GB	Q4_K_S
GRAM-Qwen3-4B-RewardModel.Q5_K_M.gguf	2.89 GB	Q5_K_M
GRAM-Qwen3-4B-RewardModel.Q5_K_S.gguf	2.82 GB	Q5_K_S
GRAM-Qwen3-4B-RewardModel.Q6_K.gguf	3.31 GB	Q6_K
GRAM-Qwen3-4B-RewardModel.Q8_0.gguf	4.28 GB	Q8_0