Instructions to use NewSonnet/omarchy-nano-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NewSonnet/omarchy-nano-2b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="NewSonnet/omarchy-nano-2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NewSonnet/omarchy-nano-2b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NewSonnet/omarchy-nano-2b 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 NewSonnet/omarchy-nano-2b:F16
# Run inference directly in the terminal:
llama cli -hf NewSonnet/omarchy-nano-2b:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NewSonnet/omarchy-nano-2b:F16
# Run inference directly in the terminal:
llama cli -hf NewSonnet/omarchy-nano-2b:F16

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 NewSonnet/omarchy-nano-2b:F16
# Run inference directly in the terminal:
./llama-cli -hf NewSonnet/omarchy-nano-2b:F16

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 NewSonnet/omarchy-nano-2b:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NewSonnet/omarchy-nano-2b:F16

Use Docker

docker model run hf.co/NewSonnet/omarchy-nano-2b:F16

LM Studio
Jan

vLLM

How to use NewSonnet/omarchy-nano-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NewSonnet/omarchy-nano-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NewSonnet/omarchy-nano-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NewSonnet/omarchy-nano-2b:F16

SGLang

How to use NewSonnet/omarchy-nano-2b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "NewSonnet/omarchy-nano-2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NewSonnet/omarchy-nano-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "NewSonnet/omarchy-nano-2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NewSonnet/omarchy-nano-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use NewSonnet/omarchy-nano-2b with Ollama:
```
ollama run hf.co/NewSonnet/omarchy-nano-2b:F16
```
Unsloth Desktop

How to use NewSonnet/omarchy-nano-2b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NewSonnet/omarchy-nano-2b:F16

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": "NewSonnet/omarchy-nano-2b:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NewSonnet/omarchy-nano-2b with Docker Model Runner:
```
docker model run hf.co/NewSonnet/omarchy-nano-2b:F16
```

Lemonade

How to use NewSonnet/omarchy-nano-2b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NewSonnet/omarchy-nano-2b:F16

Run and chat with the model

lemonade run user.omarchy-nano-2b-F16

List all available models

lemonade list

Hermes Agent

How to use NewSonnet/omarchy-nano-2b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NewSonnet/omarchy-nano-2b:F16

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 NewSonnet/omarchy-nano-2b:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NewSonnet/omarchy-nano-2b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NewSonnet/omarchy-nano-2b:F16

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 "NewSonnet/omarchy-nano-2b:F16" \
  --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"

Omarchy Nano 2B

Omarchy Nano 2B is an experimental, Omarchy-focused fine-tune of Qwen3.5-2B-Base. It is intended to answer questions about Omarchy configuration, commands, applications, and workflows. It is not an official Omarchy project.

Artifacts

gguf-q4_k_m/omarchy-nano.Q4_K_M.gguf — approximately 1.25 GB; intended for llama.cpp-compatible local inference.
gguf-q4_k_m/omarchy-nano.F16-mmproj.gguf — optional multimodal projector.
adapter/ — QLoRA adapter, tokenizer, processor configuration, and training metadata.

For low-memory or potato PCs, download only the Q4_K_M GGUF. The projector is only needed by compatible multimodal runners that accept image input.

Training data

The dataset contains 296 examples derived from 51 non-empty Markdown files from the Omarchy manual.

Training split: 259 examples
Evaluation split: 37 examples
Split method: document-level
Omarchy source commit: d3d23fdddef846ebb98b52122a6ece66211c0daf
Image references were replaced with [image omitted]; training was text-only.

Training configuration

Method: 4-bit QLoRA
LoRA rank: 16
Trainable parameters: 10,911,744 (0.49%)
Epochs: 2
Maximum sequence length: 512
Effective batch size: 8
Learning rate: 2e-4
Optimizer: 8-bit AdamW
Hardware: Google Colab Tesla T4

Final optimization metrics:

Training loss: 1.6297
Evaluation loss: 1.6660

These are optimization metrics, not a task-accuracy benchmark.

Usage with llama.cpp

Download the Q4_K_M file and run it with a llama.cpp-compatible runner:

wget -O omarchy-nano.Q4_K_M.gguf \
  https://huggingface.co/NewSonnet/omarchy-nano-2b/resolve/main/gguf-q4_k_m/omarchy-nano.Q4_K_M.gguf

llama-cli -m omarchy-nano.Q4_K_M.gguf -cnv

The adapter/ directory is a LoRA adapter and must be loaded on the base model with a PEFT-compatible Transformers workflow; it is not a standalone model.

Limitations

This is a small experimental model. It may provide incorrect commands, omit important context, or hallucinate configuration details. Verify commands against the current Omarchy documentation before running them, especially for system or security-sensitive changes.

The training data was text-only. The included projector does not mean that this fine-tune was trained for image understanding.

Reproducibility files

omarchy-nano.ipynb — cleaned, credential-free Colab training notebook.
requirements-colab.txt — pinned top-level training dependencies.
scripts/prepare_omarchy_data.py — image-sanitizing, document-level JSONL preprocessing path.
data/PROVENANCE.json — source commit, dataset counts, and run settings.
evaluation/results.json — recorded held-out loss from the completed run.

The notebook reuses an existing Drive dataset when present. If it is absent, it rebuilds a sanitized baseline from the pinned Omarchy source snapshot; the reference counts in the provenance and evaluation files describe the completed run, not a guarantee that every fresh preprocessing run will produce identical counts.

Model weights, checkpoints, and credentials are intentionally excluded from this GitHub repository. They are published separately on Hugging Face.

Licensing and attribution

The base Qwen3.5-2B-Base model is released under Apache-2.0. The Omarchy source material is released under the MIT License. Users must comply with both licenses and retain the relevant attribution.

Base model: https://huggingface.co/Qwen/Qwen3.5-2B-Base
Omarchy source: https://github.com/omacom/omarchy
Reproducibility project: https://github.com/EF-Code/omarchy-nano

Downloads last month: -

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for NewSonnet/omarchy-nano-2b

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

(70)

this model