Instructions to use OrionLLM/GRM2-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OrionLLM/GRM2-3b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OrionLLM/GRM2-3b-GGUF",
	filename="GRM2-3b.i1-IQ1_M.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 OrionLLM/GRM2-3b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf OrionLLM/GRM2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OrionLLM/GRM2-3b-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 OrionLLM/GRM2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OrionLLM/GRM2-3b-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 OrionLLM/GRM2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OrionLLM/GRM2-3b-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 OrionLLM/GRM2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OrionLLM/GRM2-3b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/OrionLLM/GRM2-3b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use OrionLLM/GRM2-3b-GGUF with Ollama:
```
ollama run hf.co/OrionLLM/GRM2-3b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use OrionLLM/GRM2-3b-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 OrionLLM/GRM2-3b-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 OrionLLM/GRM2-3b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for OrionLLM/GRM2-3b-GGUF to start chatting

Pi new

How to use OrionLLM/GRM2-3b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf OrionLLM/GRM2-3b-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": "OrionLLM/GRM2-3b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OrionLLM/GRM2-3b-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 OrionLLM/GRM2-3b-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 OrionLLM/GRM2-3b-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use OrionLLM/GRM2-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/OrionLLM/GRM2-3b-GGUF:Q4_K_M
```

Lemonade

How to use OrionLLM/GRM2-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OrionLLM/GRM2-3b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GRM2-3b-GGUF-Q4_K_M

List all available models

lemonade list

GRM2

logo

1. Introduction

GRM2 is a 3B-parameter AI designed for general-purpose, reasoning-focused tasks, with a strong emphasis on improving multi-domain reasoning across code, mathematics, science, and complex knowledge tasks. It is optimized for handling long chains of thought, enabling more structured, accurate, and reliable reasoning over difficult problems.

Despite its compact size, the model achieves strong benchmark performance, making it an efficient choice for users who want a balance between reasoning quality, versatility, and deployability.

2. Key Capabilities

Deep Reasoning at Speed: GRM2 delivers high performance on reasoning-heavy and complex tasks, with the ability to compete with — and in some cases surpass — much larger 30B-class models.
A Robust Engine for Coding & Agents: Despite having only 3B parameters, GRM2 can generate large, consistent code outputs and is an excellent choice for agentic workflows running on personal devices.
Accessible Local Deployment: Optimized for accessibility, GRM2 brings elite-level intelligence to local environments, making it a strong option for local inference across a wide range of hardware.
Efficient Long Context: The model supports a cost-efficient 256K context window, enabling long, chronologically consistent chains of reasoning with strong introspective capabilities.

3. Performance

The GRM2 delivers performance equivalent to larger models, while remaining open, small, and efficient.

logo

Detailed Benchmarks

Model	LiveCodeBench v6	HMMT Nov 25	GPQA / GPQA Diamond	MultiChallenge	AIME 2026	xBench-DeepSearch-2510	BFCL-V4
OrionLLM/GRM2-3b	76.9	77.92	83.8	52.21	87.40	39.0	56.5
Qwen/Qwen3-32B	55.7	57.08	68.4	38.72	75.83	8	47.90
OpenAI/o3-mini	76.4	N/A	79.7	39.89	86.5	N/A	65.12

Downloads last month: 695

GGUF

Model size

4B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for OrionLLM/GRM2-3b-GGUF

Unable to build the model tree, the base model loops to the model itself. Learn more.

Collection including OrionLLM/GRM2-3b-GGUF

GRM2

Collection

Powerfull Reasoning-focused models for general reasoning and agentic tasks. • 2 items • Updated 25 days ago • 5