Instructions to use AmarettoLabs/Amaretto-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AmarettoLabs/Amaretto-3B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AmarettoLabs/Amaretto-3B",
	filename="amaretto-3b-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 AmarettoLabs/Amaretto-3B 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 AmarettoLabs/Amaretto-3B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AmarettoLabs/Amaretto-3B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AmarettoLabs/Amaretto-3B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AmarettoLabs/Amaretto-3B: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 AmarettoLabs/Amaretto-3B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AmarettoLabs/Amaretto-3B: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 AmarettoLabs/Amaretto-3B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AmarettoLabs/Amaretto-3B:Q4_K_M

Use Docker

docker model run hf.co/AmarettoLabs/Amaretto-3B:Q4_K_M

LM Studio
Jan

vLLM

How to use AmarettoLabs/Amaretto-3B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AmarettoLabs/Amaretto-3B:Q4_K_M

Ollama
How to use AmarettoLabs/Amaretto-3B with Ollama:
```
ollama run hf.co/AmarettoLabs/Amaretto-3B:Q4_K_M
```

Unsloth Studio

How to use AmarettoLabs/Amaretto-3B 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 AmarettoLabs/Amaretto-3B 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 AmarettoLabs/Amaretto-3B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AmarettoLabs/Amaretto-3B to start chatting

How to use AmarettoLabs/Amaretto-3B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AmarettoLabs/Amaretto-3B: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": "AmarettoLabs/Amaretto-3B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AmarettoLabs/Amaretto-3B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AmarettoLabs/Amaretto-3B: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 AmarettoLabs/Amaretto-3B:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use AmarettoLabs/Amaretto-3B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AmarettoLabs/Amaretto-3B:Q4_K_M

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 "AmarettoLabs/Amaretto-3B:Q4_K_M" \
  --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"

Docker Model Runner
How to use AmarettoLabs/Amaretto-3B with Docker Model Runner:
```
docker model run hf.co/AmarettoLabs/Amaretto-3B:Q4_K_M
```

Lemonade

How to use AmarettoLabs/Amaretto-3B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AmarettoLabs/Amaretto-3B:Q4_K_M

Run and chat with the model

lemonade run user.Amaretto-3B-Q4_K_M

List all available models

lemonade list

Amaretto 3B

Amaretto 3B is a fine-tuned language model by AmarettoLabs, built for literary writing and writing assistance. It is fine-tuned from Ministral 3 3B Instruct using QLoRA.

The Amaretto line is designed to run on everyday hardware. Amaretto 3B is the lightest model in the family — well-suited for constrained devices, edge deployments, and local use.

Website: amaretto.ai · Contact: hello@amarettolabs.com

What it's good at

Literary prose — scene writing, character voice, emotional interiority
Writing assistance — editing, tone adjustment, conciseness, clarity, line editing
Continuation — picking up a passage and extending it in the same register
Style transfer — shifting a piece between registers (formal ↔ casual, journalistic ↔ personal)

Intended use

Amaretto 3B is a general-purpose writing companion. It works out of the box with no system prompt. For the strongest literary output, you can use the system prompt it was trained with:

You are a skilled literary fiction writer. Write with precision,
emotional depth, and a strong sense of voice. Favor showing over telling.
Use plain, direct language — avoid similes, forced comparisons, and
decorative imagery.

You can replace or extend this prompt for your own use case.

Usage

With llama.cpp / Ollama (GGUF)

GGUF quantized versions are available in this repository:

File	Size	Notes
`amaretto-3b-Q8_0.gguf`	~3.6 GB	Near-lossless; recommended where memory allows
`amaretto-3b-Q5_K_M.gguf`	~2.4 GB	Strong quality on everyday hardware
`amaretto-3b-Q4_K_M.gguf`	~2.1 GB	Smallest recommended quantization

llama-cli -m amaretto-3b-Q8_0.gguf \
  --ctx-size 4096 \
  -sys "You are a skilled literary fiction writer." \
  -p "Write the opening of a scene where a woman returns to her childhood home."

Sampling: --temp 0.8 --min-p 0.1 works well for creative writing. min-p sampling is recommended over top-k/top-p — it noticeably reduces token-level glitches on small models.

With `transformers`

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "AmarettoLabs/Amaretto-3B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": "You are a skilled literary fiction writer. Write with precision, emotional depth, and a strong sense of voice."},
    {"role": "user", "content": "Write the opening of a scene where a woman returns to her childhood home after many years away."},
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
output = model.generate(input_ids, max_new_tokens=512, temperature=0.8, do_sample=True)
print(tokenizer.decode(output[0][input_ids.shape[-1]:], skip_special_tokens=True))

Training details

Property	Value
Base model	mistralai/Ministral-3-3B-Instruct-2512
Method	QLoRA (4-bit NF4)
Framework	Unsloth + TRL SFTTrainer
LoRA rank / alpha	16 / 16
Epochs	2
Sequence length	2048
Training examples	~14,300
Eval loss	1.671

Training data consists of semi-synthetic and full-synthetic literary prose examples, writing assistance examples (editing, tone, clarity, continuation).

The base model is multimodal (3.4B language model + 0.4B vision encoder). Amaretto 3B's fine-tuning targets text only; vision capability is not a focus of this release.

Limitations

Optimized for English prose; other languages are not a focus
A 3B-class model has clear knowledge and reasoning limits — it is a writing tool, not a factual reference
The model may occasionally ignore system prompt instructions on complex or conflicting requests
Outputs can reflect biases present in the base model and training data

About AmarettoLabs

AmarettoLabs is a small independent group based in California, USA, specializing in small language models and AI on the edge. The Amaretto line is released free and open.

Website: amaretto.ai · Contact: hello@amarettolabs.com

License

This model is released under the Apache 2.0 License, inherited from the base model. Base model: Ministral 3 3B by Mistral AI.

Downloads last month: 762

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for AmarettoLabs/Amaretto-3B

Base model

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

Quantized

mistralai/Ministral-3-3B-Instruct-2512

Quantized

(42)

this model

Quantizations

2 models

Amaretto 3B

What it's good at

Intended use

Usage

With llama.cpp / Ollama (GGUF)

With transformers

Training details

Limitations

About AmarettoLabs

License

Model tree for AmarettoLabs/Amaretto-3B

With `transformers`