Instructions to use CorelynAI/NeoMini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CorelynAI/NeoMini with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CorelynAI/NeoMini",
	filename="NeoMini_3B.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use CorelynAI/NeoMini with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CorelynAI/NeoMini
# Run inference directly in the terminal:
llama-cli -hf CorelynAI/NeoMini

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CorelynAI/NeoMini
# Run inference directly in the terminal:
llama-cli -hf CorelynAI/NeoMini

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 CorelynAI/NeoMini
# Run inference directly in the terminal:
./llama-cli -hf CorelynAI/NeoMini

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 CorelynAI/NeoMini
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CorelynAI/NeoMini

Use Docker

docker model run hf.co/CorelynAI/NeoMini

LM Studio
Jan

vLLM

How to use CorelynAI/NeoMini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CorelynAI/NeoMini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CorelynAI/NeoMini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CorelynAI/NeoMini

Ollama
How to use CorelynAI/NeoMini with Ollama:
```
ollama run hf.co/CorelynAI/NeoMini
```

Unsloth Studio new

How to use CorelynAI/NeoMini 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 CorelynAI/NeoMini 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 CorelynAI/NeoMini to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CorelynAI/NeoMini to start chatting

Pi new

How to use CorelynAI/NeoMini with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf CorelynAI/NeoMini

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": "NeoMini"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CorelynAI/NeoMini with Docker Model Runner:
```
docker model run hf.co/CorelynAI/NeoMini
```

Lemonade

How to use CorelynAI/NeoMini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CorelynAI/NeoMini

Run and chat with the model

lemonade run user.NeoMini-{{QUANT_TAG}}

List all available models

lemonade list

Corelyn NeoMini GGUF Model

Specifications :

Model Name: Corelyn NeoMini
Base Name: NeoMini-3B
Type: Instruct / Fine-tuned
Architecture: Ministral-3
Size: 3B parameters
Organization: Corelyn

Model Overview

Corelyn NeoMini is a 3-billion parameter LLaMA-based instruction-tuned model, designed for general-purpose assistant tasks and knowledge extraction. It is a fine-tuned variant optimized for instruction-following use cases.

Fine-tuning type: Instruct
Base architecture: Ministral-3
Parameter count: 3B

This model is suitable for applications such as:

Chatbots and conversational AI
Knowledge retrieval and Q&A
Code and text generation
Instruction-following tasks

Usage

Download from : NeoMini3.2


# pip install pip install llama-cpp-python

from llama_cpp import Llama

# Load the model (update the path to where your .gguf file is)
llm = Llama(model_path="path/to/the/file/NeoMini_3B.gguf")

# Create chat completion
response = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Create a Haiku about AI"}]
)

# Print the generated text
print(response.choices[0].message["content"])

Downloads last month: 19

GGUF

Model size

3B params

Architecture

mistral3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for CorelynAI/NeoMini

Base model

mistralai/Ministral-3-3B-Base-2512

Quantized

(29)

this model