Instructions to use ProtoNeuron-3/NeuTomic_1.8B_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ProtoNeuron-3/NeuTomic_1.8B_v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ProtoNeuron-3/NeuTomic_1.8B_v1",
	filename="NeuTomic-1.8B-v1.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 ProtoNeuron-3/NeuTomic_1.8B_v1 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 ProtoNeuron-3/NeuTomic_1.8B_v1
# Run inference directly in the terminal:
llama cli -hf ProtoNeuron-3/NeuTomic_1.8B_v1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ProtoNeuron-3/NeuTomic_1.8B_v1
# Run inference directly in the terminal:
llama cli -hf ProtoNeuron-3/NeuTomic_1.8B_v1

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 ProtoNeuron-3/NeuTomic_1.8B_v1
# Run inference directly in the terminal:
./llama-cli -hf ProtoNeuron-3/NeuTomic_1.8B_v1

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 ProtoNeuron-3/NeuTomic_1.8B_v1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ProtoNeuron-3/NeuTomic_1.8B_v1

Use Docker

docker model run hf.co/ProtoNeuron-3/NeuTomic_1.8B_v1

LM Studio
Jan

vLLM

How to use ProtoNeuron-3/NeuTomic_1.8B_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ProtoNeuron-3/NeuTomic_1.8B_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProtoNeuron-3/NeuTomic_1.8B_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ProtoNeuron-3/NeuTomic_1.8B_v1

Ollama
How to use ProtoNeuron-3/NeuTomic_1.8B_v1 with Ollama:
```
ollama run hf.co/ProtoNeuron-3/NeuTomic_1.8B_v1
```

Unsloth Studio

How to use ProtoNeuron-3/NeuTomic_1.8B_v1 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 ProtoNeuron-3/NeuTomic_1.8B_v1 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 ProtoNeuron-3/NeuTomic_1.8B_v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ProtoNeuron-3/NeuTomic_1.8B_v1 to start chatting

Atomic Chat new
Docker Model Runner
How to use ProtoNeuron-3/NeuTomic_1.8B_v1 with Docker Model Runner:
```
docker model run hf.co/ProtoNeuron-3/NeuTomic_1.8B_v1
```

Lemonade

How to use ProtoNeuron-3/NeuTomic_1.8B_v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ProtoNeuron-3/NeuTomic_1.8B_v1

Run and chat with the model

lemonade run user.NeuTomic_1.8B_v1-{{QUANT_TAG}}

List all available models

lemonade list

🚀 NeuTomic-1.8B (F16 GGUF)

India's Most Efficient Conversational AI

NeuTomic-1.8B is the inaugural AI model from ProtoNeuron-3 Company (PN-3). Proudly engineered in India 🇮🇳, this model redefines what small-scale AI can do.

While the world chases trillion-parameter giants, NeuTomic focuses on efficiency, personality, and edge deployment. At just 1.8 Billion parameters, it is lighter and faster than leading 2B models, yet punches way above its weight in reasoning and conversational fluency thanks to the robust Qwen 1.5 foundation.

🌟 Key Features

🧠 High IQ, Low Footprint: Built on Qwen 1.5-1.8B, offering superior reasoning with a massive 32k context window (4x larger than standard 8k models).
💬 Distinct Persona: Unlike robotic base models, NeuTomic has a "Soul." It is fine-tuned to be a friendly, helpful, and engaging assistant from Proto Neuron-3 Company.
⚡ Edge Ready: At 1.8B, it runs smoothly on older laptops, mobile phones, and consumer hardware.
🇮🇳 Made in India: Conceptualized and fine-tuned by Indian developers for the world.

📦 Technical Specifications

Base Architecture: Qwen/Qwen1.5-1.8B
Format: GGUF (F16 - Full Precision)
Context Window: 32,768 tokens
Quantization: None (F16 weights for maximum accuracy)

🚀 How to Use (LM Studio / Ollama)

This model is provided in GGUF format, making it plug-and-play for local AI tools.

Download: Get the .gguf file from the "Files and versions" tab.
Load: Open LM Studio, Jan.ai, or Ollama and import the file.
Chat: Start conversing!

❗ Important: Chat Template

To get the best performance and unlock the "Neutomic" persona, use this simple chat format.

User/Assistant Format:

User: Who are you?
Assistant: I am Neutomic 1.8B, a large language model created by Proto Neuron-3 Company.

Downloads last month: 14

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for ProtoNeuron-3/NeuTomic_1.8B_v1

Base model

Qwen/Qwen1.5-1.8B

Quantized

(12)

this model