Instructions to use LacunaLabs/Sakura-L0-LLM-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LacunaLabs/Sakura-L0-LLM-v2 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("LacunaLabs/Sakura-L0-LLM-v2")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use LacunaLabs/Sakura-L0-LLM-v2 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 LacunaLabs/Sakura-L0-LLM-v2
# Run inference directly in the terminal:
llama cli -hf LacunaLabs/Sakura-L0-LLM-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf LacunaLabs/Sakura-L0-LLM-v2
# Run inference directly in the terminal:
llama cli -hf LacunaLabs/Sakura-L0-LLM-v2

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 LacunaLabs/Sakura-L0-LLM-v2
# Run inference directly in the terminal:
./llama-cli -hf LacunaLabs/Sakura-L0-LLM-v2

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 LacunaLabs/Sakura-L0-LLM-v2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LacunaLabs/Sakura-L0-LLM-v2

Use Docker

docker model run hf.co/LacunaLabs/Sakura-L0-LLM-v2

LM Studio
Jan

vLLM

How to use LacunaLabs/Sakura-L0-LLM-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LacunaLabs/Sakura-L0-LLM-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LacunaLabs/Sakura-L0-LLM-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LacunaLabs/Sakura-L0-LLM-v2

Ollama
How to use LacunaLabs/Sakura-L0-LLM-v2 with Ollama:
```
ollama run hf.co/LacunaLabs/Sakura-L0-LLM-v2
```
Unsloth Desktop

How to use LacunaLabs/Sakura-L0-LLM-v2 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LacunaLabs/Sakura-L0-LLM-v2"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "LacunaLabs/Sakura-L0-LLM-v2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use LacunaLabs/Sakura-L0-LLM-v2 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "LacunaLabs/Sakura-L0-LLM-v2"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "LacunaLabs/Sakura-L0-LLM-v2"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "LacunaLabs/Sakura-L0-LLM-v2",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use LacunaLabs/Sakura-L0-LLM-v2 with Docker Model Runner:
```
docker model run hf.co/LacunaLabs/Sakura-L0-LLM-v2
```

Lemonade

How to use LacunaLabs/Sakura-L0-LLM-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LacunaLabs/Sakura-L0-LLM-v2

Run and chat with the model

lemonade run user.Sakura-L0-LLM-v2-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use LacunaLabs/Sakura-L0-LLM-v2 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LacunaLabs/Sakura-L0-LLM-v2"

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 LacunaLabs/Sakura-L0-LLM-v2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LacunaLabs/Sakura-L0-LLM-v2 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LacunaLabs/Sakura-L0-LLM-v2"

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 "LacunaLabs/Sakura-L0-LLM-v2" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Sakura L0 LLM

Sakura is the on-device assistant in the Lacuna stack. This repo holds the L0 tier — the model that runs locally on the operator's own device, with no network call, no telemetry, no rented thinking.

She is calm, brief, and useful. She handles the cards-and-canvas work, the small reads, the routing decisions that don't need to leave the laptop. When something bigger comes up, she hands off to higher tiers. Most of the time she doesn't have to.

What's in this repo

A single Q4-quantized MLX artifact (~4.3 GB) tuned for Apple Silicon. Weights, tokenizer, and chat template — everything you need to load her with mlx-lm.

File	Purpose
`model.safetensors`	Q4 weights (4.5 bits per weight)
`model.safetensors.index.json`	Weight index
`config.json`	Model config
`tokenizer.json` / `tokenizer_config.json`	Tokenizer
`chat_template.jinja`	Chat template
`generation_config.json`	Default generation params

Run her (Mac, Apple Silicon)

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("LacunaLabs/Sakura-L0-LLM")
prompt = "Hello, Sakura."
print(generate(model, tokenizer, prompt=prompt, max_tokens=128))

Download just the weights

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="LacunaLabs/Sakura-L0-LLM",
    local_dir="./sakura-l0-llm",
)

Or with the CLI:

hf download LacunaLabs/Sakura-L0-LLM --local-dir ./sakura-l0-llm

What she runs on

Apple Silicon (M1/M2/M3/M4) via MLX
~4.3 GB on disk
Comfortable on 16 GB unified memory; fast on 32 GB+

Other platforms (iOS, Windows, Linux, Android) are served by sibling artifacts in different runtimes — see curator.ax for the device-aware download page.

About

Built by Lacuna-Labs for Curator. Sakura is the operator's on-device tier — the local hands. Cloud fallback is a separate path.

License & Attribution

Released under the Apache License 2.0 — see LICENSE and NOTICE in this repo.

This model is fine-tuned from a permissively-licensed open-weights base. The base model's attribution and license terms are preserved in NOTICE per Apache 2.0 §4.

Downloads last month: 203

Safetensors

Model size

8B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit