Instructions to use apothic/bonsai-8B-1bit-turboquant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apothic/bonsai-8B-1bit-turboquant with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="apothic/bonsai-8B-1bit-turboquant",
	filename="models/gguf/8B/Bonsai-8B.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use apothic/bonsai-8B-1bit-turboquant with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf apothic/bonsai-8B-1bit-turboquant
# Run inference directly in the terminal:
llama-cli -hf apothic/bonsai-8B-1bit-turboquant

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf apothic/bonsai-8B-1bit-turboquant
# Run inference directly in the terminal:
llama-cli -hf apothic/bonsai-8B-1bit-turboquant

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 apothic/bonsai-8B-1bit-turboquant
# Run inference directly in the terminal:
./llama-cli -hf apothic/bonsai-8B-1bit-turboquant

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 apothic/bonsai-8B-1bit-turboquant
# Run inference directly in the terminal:
./build/bin/llama-cli -hf apothic/bonsai-8B-1bit-turboquant

Use Docker

docker model run hf.co/apothic/bonsai-8B-1bit-turboquant

LM Studio
Jan
Ollama
How to use apothic/bonsai-8B-1bit-turboquant with Ollama:
```
ollama run hf.co/apothic/bonsai-8B-1bit-turboquant
```

Unsloth Studio

How to use apothic/bonsai-8B-1bit-turboquant 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 apothic/bonsai-8B-1bit-turboquant 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 apothic/bonsai-8B-1bit-turboquant to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for apothic/bonsai-8B-1bit-turboquant to start chatting

How to use apothic/bonsai-8B-1bit-turboquant with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf apothic/bonsai-8B-1bit-turboquant

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": "apothic/bonsai-8B-1bit-turboquant"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use apothic/bonsai-8B-1bit-turboquant with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf apothic/bonsai-8B-1bit-turboquant

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 apothic/bonsai-8B-1bit-turboquant

Run Hermes

hermes

Docker Model Runner
How to use apothic/bonsai-8B-1bit-turboquant with Docker Model Runner:
```
docker model run hf.co/apothic/bonsai-8B-1bit-turboquant
```

Lemonade

How to use apothic/bonsai-8B-1bit-turboquant with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull apothic/bonsai-8B-1bit-turboquant

Run and chat with the model

lemonade run user.bonsai-8B-1bit-turboquant-{{QUANT_TAG}}

List all available models

lemonade list

Bonsai 1-Bit TurboQuant

This repository bundles the Bonsai-8B GGUF checkpoint and the launcher scripts needed to run it with the TurboQuant-enabled llama.cpp fork.

TurboQuant does not change the 1-bit model weights. It changes the KV cache format at runtime, which is what reduces VRAM usage.

What is included

models/gguf/8B/Bonsai-8B.gguf
scripts/common.sh
scripts/run_llama.sh
scripts/start_llama_server.sh
scripts/start_openwebui.sh
scripts/download_models.sh

Quick Start

Clone this repo and the TurboQuant llama.cpp fork side by side:

git clone https://github.com/Apothic-AI/bonsai-turboquant.git
git clone https://github.com/Apothic-AI/llama.cpp-1bit-turboquant.git ../llama.cpp-1bit-turboquant
cd bonsai-turboquant

Build the forked llama.cpp checkout with CUDA:

cd ../llama.cpp-1bit-turboquant
cmake -S . -B build-tbq-cuda -DGGML_CUDA=ON -DLLAMA_BUILD_SERVER=ON -DLLAMA_BUILD_TOOLS=ON
cmake --build build-tbq-cuda -j
cd ../bonsai-turboquant

Run Bonsai through the TurboQuant-enabled server:

BONSAI_LLAMA_BIN_DIR=../llama.cpp-1bit-turboquant/build-tbq-cuda/bin \
BONSAI_CACHE_TYPE_K=tbq4_0 \
BONSAI_CACHE_TYPE_V=tbq3_0 \
./scripts/start_llama_server.sh

The same override works for direct prompts:

BONSAI_LLAMA_BIN_DIR=../llama.cpp-1bit-turboquant/build-tbq-cuda/bin \
BONSAI_CACHE_TYPE_K=tbq4_0 \
BONSAI_CACHE_TYPE_V=tbq3_0 \
./scripts/run_llama.sh -p "Who are you?"

If you want the browser UI, start ./scripts/start_openwebui.sh after the server is running.

To fetch the 4B or 1.7B checkpoints later, use ./scripts/download_models.sh.

Notes

This repo includes the 8B GGUF only.
Set BONSAI_MODEL to 8B unless you have added additional model downloads locally.
The llama.cpp fork contains the TurboQuant runtime support.

Downloads last month: 293

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support