Instructions to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF 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 darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0
# Run inference directly in the terminal:
llama cli -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0
# Run inference directly in the terminal:
llama cli -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_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 darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0
# Run inference directly in the terminal:
./llama-cli -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_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 darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0

Use Docker

docker model run hf.co/darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0

LM Studio
Jan
Ollama
How to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF with Ollama:
```
ollama run hf.co/darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0
```
Unsloth Desktop

How to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0

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": "darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF with Docker Model Runner:
```
docker model run hf.co/darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0
```

Lemonade

How to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0

Run and chat with the model

lemonade run user.AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF-Q2_0

List all available models

lemonade list

Hermes Agent

How to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_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 darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_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 "darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF:Q2_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"

AJAN-SIMIT Ternary-Bonsai Q2_0 (GGUF)

Q2_0 GGUF quantizations of Prism ML's Ternary-Bonsai model family, produced by DarkStar Initiative for the Ajan Simit offline mobile AI project (an on-device Android voice assistant).

We did not train or create the base model. This repository contains only our own re-quantization of Prism ML's publicly released weights, done so the model is small enough to run entirely on-device on a phone.

Provenance / credits

Base model: Qwen3-1.7B (Apache 2.0, Qwen team)
Ternary fine-tune: prism-ml/Ternary-Bonsai (Apache 2.0, Prism ML)
This Q2_0 re-quantization: DarkStar Initiative / Ajan Simit, produced with a self-built llama-quantize from Prism ML's own fork, PrismML-Eng/llama.cpp (prism branch) -- credited per their own model card's request.
License: Apache 2.0, inherited unchanged from the base model and the fine-tune. No added restrictions. A full copy of the license text is included in this repo as LICENSE.

If you use the original Ternary-Bonsai model itself (not just this re-quantization), please cite Prism ML directly:

@techreport{ternarybonsai,
  title  = {Ternary Bonsai: 1.58-bit Language Models},
  author = {Prism ML},
}

What's different from the upstream Prism ML release

Only the quantization level and the file/repo naming:

Quantization: Q2_0 (2.125 bpw), quantized from Prism ML's F16 release. No retraining, no architecture changes, no fine-tuning of our own.
Naming: the AJAN-SIMIT- prefix marks these files as our own community re-quantization and build, produced for the Ajan Simit app specifically -- not an official Prism ML release, and not endorsed by Prism ML or the Qwen team.

Files

File	Size
`AJAN-SIMIT-Ternary-Bonsai-1.7B-Q2_0.gguf`	~463 MB
`AJAN-SIMIT-Ternary-Bonsai-4B-Q2_0.gguf`	~1.07 GB
`AJAN-SIMIT-Ternary-Bonsai-8B-Q2_0.gguf`	~2.18 GB
`AJAN-SIMIT-Ternary-Bonsai-27B-Q2_0.gguf`	~8.25 GB

Usage

Compatible with any recent llama.cpp-based inference engine. Q2_0 is a first-class quant type in Prism ML's llama.cpp fork; mainline llama.cpp support may vary by version.

Downloads last month: 354

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

2-bit

Inference Providers NEW

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

Model tree for darkstarinitiative/AJAN-SIMIT-Ternary-Bonsai-Q2_0-GGUF

Base model

prism-ml/Ternary-Bonsai-1.7B-unpacked

Quantized

prism-ml/Ternary-Bonsai-1.7B-gguf

Quantized

(2)

this model