Instructions to use frupniew/macaulay2-rag-coder-3b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frupniew/macaulay2-rag-coder-3b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="frupniew/macaulay2-rag-coder-3b-gguf",
	filename="qwen2.5-coder-3b-instruct.Q4_K_M.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 frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M

Use Docker

docker model run hf.co/frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use frupniew/macaulay2-rag-coder-3b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "frupniew/macaulay2-rag-coder-3b-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": "frupniew/macaulay2-rag-coder-3b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M

Ollama
How to use frupniew/macaulay2-rag-coder-3b-gguf with Ollama:
```
ollama run hf.co/frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M
```

Unsloth Studio

How to use frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-3b-gguf to start chatting

How to use frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-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": "frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-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 frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use frupniew/macaulay2-rag-coder-3b-gguf with Docker Model Runner:
```
docker model run hf.co/frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M
```

Lemonade

How to use frupniew/macaulay2-rag-coder-3b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull frupniew/macaulay2-rag-coder-3b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.macaulay2-rag-coder-3b-gguf-Q4_K_M

List all available models

lemonade list

Macaulay2 RAG-Coder 3B (GGUF)

This repository contains the Q4_K_M GGUF quantized weights of a specialized coding model fine-tuned for Macaulay2 (a software system for research in algebraic geometry and commutative algebra).

Designed specifically for Edge Deployment, this model fits comfortably within a 4GB VRAM constraint while maintaining high fidelity in mathematical reasoning and domain-specific syntax.

🧠 Model Details & Engineering Choices

Base Model: Qwen2.5-Coder-3B-Instruct
Quantization: Q4_K_M (~1.9GB). Chosen over AWQ to avoid CUDA OOM during calibration on constrained hardware (Colab T4) and to guarantee safe inference on 4GB VRAM consumer GPUs using llama.cpp / vLLM.
Context Window: 4096 tokens (optimized for RAG context injection).
Domain Quirk Handled: Macaulay2's --script mode is notoriously silent and does not auto-print the last expression. This model was explicitly trained to append << result << endl; to ensure deterministic stdout capture in automated evaluation pipelines.

🚀 Quick Start (Ollama)

A Modelfile is included in this repository for immediate local testing.

ollama create m2-coder -f Modelfile
ollama run m2-coder "Write a script to compute the Groebner basis of ideal(x^2-y, y^2-z) in ZZ/5[x,y,z]"

🏗️ Architecture & Ecosystem

This model is the core generation engine of a broader Data-Centric RAG Pipeline: 🔌 LoRA Adapter (Safetensors): frupniew/macaulay2-rag-coder-3b-adapter 📚 RAG Knowledge Base: frupniew/macaulay2-rag-chunks 📝 Instruct Dataset: frupniew/macaulay2-qa-instruct

Downloads last month: 245

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for frupniew/macaulay2-rag-coder-3b-gguf

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Quantized

(101)

this model

frupniew
/

macaulay2-rag-coder-3b-gguf

Macaulay2 RAG-Coder 3B (GGUF)

🧠 Model Details & Engineering Choices

🚀 Quick Start (Ollama)

🏗️ Architecture & Ecosystem

Model tree for frupniew/macaulay2-rag-coder-3b-gguf

Dataset used to train frupniew/macaulay2-rag-coder-3b-gguf