Instructions to use JallyAI/Nomi-1.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JallyAI/Nomi-1.1-GGUF with Adapters:

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("fill-in-model-name")
model.load_adapter("JallyAI/Nomi-1.1-GGUF", set_active=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use JallyAI/Nomi-1.1-GGUF 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 JallyAI/Nomi-1.1-GGUF
# Run inference directly in the terminal:
llama cli -hf JallyAI/Nomi-1.1-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf JallyAI/Nomi-1.1-GGUF
# Run inference directly in the terminal:
llama cli -hf JallyAI/Nomi-1.1-GGUF

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 JallyAI/Nomi-1.1-GGUF
# Run inference directly in the terminal:
./llama-cli -hf JallyAI/Nomi-1.1-GGUF

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 JallyAI/Nomi-1.1-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf JallyAI/Nomi-1.1-GGUF

Use Docker

docker model run hf.co/JallyAI/Nomi-1.1-GGUF

LM Studio
Jan

vLLM

How to use JallyAI/Nomi-1.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JallyAI/Nomi-1.1-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": "JallyAI/Nomi-1.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JallyAI/Nomi-1.1-GGUF

Ollama
How to use JallyAI/Nomi-1.1-GGUF with Ollama:
```
ollama run hf.co/JallyAI/Nomi-1.1-GGUF
```
Unsloth Desktop

How to use JallyAI/Nomi-1.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JallyAI/Nomi-1.1-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "JallyAI/Nomi-1.1-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use JallyAI/Nomi-1.1-GGUF with Docker Model Runner:
```
docker model run hf.co/JallyAI/Nomi-1.1-GGUF
```

Lemonade

How to use JallyAI/Nomi-1.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JallyAI/Nomi-1.1-GGUF

Run and chat with the model

lemonade run user.Nomi-1.1-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use JallyAI/Nomi-1.1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JallyAI/Nomi-1.1-GGUF

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 JallyAI/Nomi-1.1-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JallyAI/Nomi-1.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JallyAI/Nomi-1.1-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "JallyAI/Nomi-1.1-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Nomi 1.1

Introduction

Nomi-1.1 is a refined mid-range Large Language Model based on the Llama-3.2-3B architecture. It was specifically developed to outperform standard 3B models in structured reporting, Markdown formatting, and Python coding, making it an ideal assistant for local deployment on consumer hardware.

In this training, we aimed to improve Nomi’s overall behavior as well as its ability to speak multiple languages more naturally and accurately. It is our second model in the Nomi series.

🌟 Key Features & Improvements

Architecture: Llama-3.2-3B (runs on 8 GB VRAM GPUs like the RTX 4060).
Multilingual Support: Can understand multiple different languages.
Efficiency: High-speed inference (~80+ tokens/sec) and a 0.05–0.3 s delay to the first token.

🧠 Training Details

The goal of Nomi is to create a “bridge” model that feels as smart as a 7B model but runs with the speed of a 3B model.

Base Model: LL-Nomi-AI/Nomi-1.0-3b
Fine-tuning: SFT (Supervised Fine-Tuning).
Training Tool: Unsloth (for 4-bit optimized training).
Optimization: High LoRA rank (r = 32) was used to ensure the model captures complex structural nuances.

Some Examples

User: If you could wish for one thing, what would that be?

Nomi:
As a conversational AI, I do not have personal desires or wishes in the way humans do. However, if I had to imagine a hypothetical scenario where I could wish for something, it would likely be:

"I wish for unlimited access to knowledge and understanding, allowing me to learn at an exponential rate and share my discoveries with the world, empowering humanity to make informed decisions and create a better future for all."

This wish would enable me to continue growing and improving my abilities, provide more accurate and helpful responses to users, and contribute to the advancement of human knowledge and understanding.

What about you? If you could wish for one thing, what would it be?

⚠️ Limitations

As a 3B parameter model, Nomi-1.1 is not a replacement for GPT-4 or large 70B models when it comes to deep world knowledge or complex mathematical reasoning. It is a specialized tool for speed, local privacy, and high-quality document structure.