Instructions to use livadies/Bonsai-27B-Android-Local with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use livadies/Bonsai-27B-Android-Local 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 livadies/Bonsai-27B-Android-Local:Q1_0
# Run inference directly in the terminal:
llama cli -hf livadies/Bonsai-27B-Android-Local:Q1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf livadies/Bonsai-27B-Android-Local:Q1_0
# Run inference directly in the terminal:
llama cli -hf livadies/Bonsai-27B-Android-Local:Q1_0

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 livadies/Bonsai-27B-Android-Local:Q1_0
# Run inference directly in the terminal:
./llama-cli -hf livadies/Bonsai-27B-Android-Local:Q1_0

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 livadies/Bonsai-27B-Android-Local:Q1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf livadies/Bonsai-27B-Android-Local:Q1_0

Use Docker

docker model run hf.co/livadies/Bonsai-27B-Android-Local:Q1_0

LM Studio
Jan

vLLM

How to use livadies/Bonsai-27B-Android-Local with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "livadies/Bonsai-27B-Android-Local"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "livadies/Bonsai-27B-Android-Local",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/livadies/Bonsai-27B-Android-Local:Q1_0

Ollama
How to use livadies/Bonsai-27B-Android-Local with Ollama:
```
ollama run hf.co/livadies/Bonsai-27B-Android-Local:Q1_0
```

Unsloth Studio

How to use livadies/Bonsai-27B-Android-Local 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 livadies/Bonsai-27B-Android-Local 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 livadies/Bonsai-27B-Android-Local to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for livadies/Bonsai-27B-Android-Local to start chatting

How to use livadies/Bonsai-27B-Android-Local with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf livadies/Bonsai-27B-Android-Local:Q1_0

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": "livadies/Bonsai-27B-Android-Local:Q1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use livadies/Bonsai-27B-Android-Local with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf livadies/Bonsai-27B-Android-Local:Q1_0

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 livadies/Bonsai-27B-Android-Local:Q1_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use livadies/Bonsai-27B-Android-Local with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf livadies/Bonsai-27B-Android-Local:Q1_0

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 "livadies/Bonsai-27B-Android-Local:Q1_0" \
  --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 livadies/Bonsai-27B-Android-Local with Docker Model Runner:
```
docker model run hf.co/livadies/Bonsai-27B-Android-Local:Q1_0
```

Lemonade

How to use livadies/Bonsai-27B-Android-Local with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull livadies/Bonsai-27B-Android-Local:Q1_0

Run and chat with the model

lemonade run user.Bonsai-27B-Android-Local-Q1_0

List all available models

lemonade list

Bonsai-27B-Android-Local / THIRD_PARTY.md

livadies

Update bilingual docs, mixed licensing notes, and model checksum / Обновить документацию, лицензии и checksum модели

a32665e verified 18 days ago

preview code

Raw

History Blame Contribute Delete

1.38 kB

Third-party components / Сторонние компоненты

English

The Android/JNI runtime is based on the examples/llama.android sample and PrismML fork of llama.cpp, pinned to commit 62061f91088281e65071cc38c5f69ee95c39f14e. Preserve the upstream MIT license when redistributing the native runtime.
models/Bonsai-27B-Q1_0.gguf is an unmodified verified copy obtained from https://huggingface.co/prism-ml/Bonsai-27B-gguf. It remains subject to the upstream Apache-2.0 license and model-card conditions.
AndroidX, Material Components, Kotlin, Gradle, NDK, and CMake retain their respective upstream licenses.

Русский

Android/JNI runtime основан на примере examples/llama.android и форке PrismML llama.cpp, закреплённом на commit 62061f91088281e65071cc38c5f69ee95c39f14e. При распространении native runtime необходимо сохранить MIT-лицензию upstream.
models/Bonsai-27B-Q1_0.gguf — неизменённая проверенная копия из https://huggingface.co/prism-ml/Bonsai-27B-gguf. Она сохраняет условия Apache-2.0 и model card исходного репозитория.
AndroidX, Material Components, Kotlin, Gradle, NDK и CMake сохраняют свои upstream-лицензии.