Instructions to use prism-ml/Ternary-Bonsai-8B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prism-ml/Ternary-Bonsai-8B-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prism-ml/Ternary-Bonsai-8B-gguf",
	filename="Ternary-Bonsai-8B-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use prism-ml/Ternary-Bonsai-8B-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prism-ml/Ternary-Bonsai-8B-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf prism-ml/Ternary-Bonsai-8B-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prism-ml/Ternary-Bonsai-8B-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf prism-ml/Ternary-Bonsai-8B-gguf:F16

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 prism-ml/Ternary-Bonsai-8B-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf prism-ml/Ternary-Bonsai-8B-gguf:F16

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 prism-ml/Ternary-Bonsai-8B-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prism-ml/Ternary-Bonsai-8B-gguf:F16

Use Docker

docker model run hf.co/prism-ml/Ternary-Bonsai-8B-gguf:F16

LM Studio
Jan

vLLM

How to use prism-ml/Ternary-Bonsai-8B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prism-ml/Ternary-Bonsai-8B-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prism-ml/Ternary-Bonsai-8B-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prism-ml/Ternary-Bonsai-8B-gguf:F16

Ollama
How to use prism-ml/Ternary-Bonsai-8B-gguf with Ollama:
```
ollama run hf.co/prism-ml/Ternary-Bonsai-8B-gguf:F16
```

Unsloth Studio new

How to use prism-ml/Ternary-Bonsai-8B-gguf 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 prism-ml/Ternary-Bonsai-8B-gguf 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 prism-ml/Ternary-Bonsai-8B-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prism-ml/Ternary-Bonsai-8B-gguf to start chatting

Pi new

How to use prism-ml/Ternary-Bonsai-8B-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prism-ml/Ternary-Bonsai-8B-gguf:F16

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": "prism-ml/Ternary-Bonsai-8B-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prism-ml/Ternary-Bonsai-8B-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prism-ml/Ternary-Bonsai-8B-gguf:F16

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 prism-ml/Ternary-Bonsai-8B-gguf:F16

Run Hermes

hermes

Docker Model Runner
How to use prism-ml/Ternary-Bonsai-8B-gguf with Docker Model Runner:
```
docker model run hf.co/prism-ml/Ternary-Bonsai-8B-gguf:F16
```

Lemonade

How to use prism-ml/Ternary-Bonsai-8B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prism-ml/Ternary-Bonsai-8B-gguf:F16

Run and chat with the model

lemonade run user.Ternary-Bonsai-8B-gguf-F16

List all available models

lemonade list

Prism ML Website | White Paper | Demo & Examples | Discord

Ternary-Bonsai-8B-gguf

Ternary (1.58-bit) language model in GGUF Q2_0 format for llama.cpp

Pareto Frontier

Resources

White Paper
Demo repo — examples for serving, benchmarking, and integrating Bonsai
Discord — community support and updates
Kernels: Q2_0 is not yet in mainline llama.cpp. Use our fork at PrismML-Eng/llama.cpp (prism branch, default) which adds Q2_0 support for CPU (NEON/generic) and Metal. Upstream PR coming soon.

Model Overview

Item	Specification
Base model	Qwen3-8B
Parameters	8.19B (~6.95B non-embedding)
Architecture	GQA (32 query / 8 KV heads), SwiGLU MLP, RoPE, RMSNorm
Layers	36 Transformer decoder blocks
Context length	65,536 tokens
Vocab size	151,936
Weight format	GGUF Q2_0 g128: {-1, 0, +1} with FP16 group-wise scaling
Packed Q2_0 size	2.03 GiB (2.18 GB)
Ternary coverage	Embeddings, attention projections, MLP projections, LM head
License	Apache 2.0

Quantization Format: GGUF Q2_0 (g128)

Each weight takes a value from {-1, 0, +1}, with one shared FP16 scale per group of 128 weights:

w_i = scale_g * t_i,    t_i in {-1, 0, +1}

Q2_0 encodes each weight as a 2-bit code q in {0, 1, 2, 3}, dequantized via w = (q - 1) * scale. One 128-element block is 34 bytes (2 bytes FP16 scale + 32 bytes of packed 2-bit codes) for an effective 2.125 bits/weight. The fourth code point (q = 3, reconstructing to +2 * scale) is reserved for future extensions; for ternary weights it is unused.

Memory

Format	Size	Reduction	Ratio
FP16	16.38 GB	--	1.0x
GGUF Q2_0 g128	2.03 GiB (2.18 GB)	86.7%	7.5x

Files in this repo

File	Format	Size	Recommended
`Ternary-Bonsai-8B-F16.gguf`	FP16	16.38 GB	baseline / re-quantization source
`Ternary-Bonsai-8B-Q2_0.gguf`	Q2_0 (g128)	2.03 GiB	recommended (lossless for ternary)

Quickstart

Build from the Prism fork

git clone https://github.com/PrismML-Eng/llama.cpp
cd llama.cpp
cmake -B build -DGGML_METAL=ON   # or -DGGML_CUDA=ON, -DGGML_VULKAN=ON
cmake --build build -j

`llama.cpp` CLI

./build/bin/llama-cli \
  -m Ternary-Bonsai-8B-Q2_0.gguf \
  -p "Explain quantum computing in simple terms." \
  -n 256

`llama.cpp` server

./build/bin/llama-server -m Ternary-Bonsai-8B-Q2_0.gguf -c 4096

Throughput (llama.cpp, Apple M4 Pro 48 GB)

Backend	PP512 (tok/s)	TG128 (tok/s)
Metal (GPU)	455	76
NEON CPU (10 t)	146	32

Flags: -ngl 99 -fa 1 for Metal; -ngl 0 -fa 1 -t 10 for CPU.

Benchmarks

Evaluated with EvalScope v1.4.2 + vLLM 0.15.1 on NVIDIA H100 under identical infrastructure, generation parameters, and scoring. All models are in the 6B-9B parameter range.

Model	Size	Avg	MMLU-R	MuSR	GSM8K	HE+	IFEval	BFCL
Qwen 3 8B	16.38 GB	79.3	83	55	93	82.3	81.5	81
Ternary Bonsai 8B	2.18 GB	75.5	72.6	56.2	91	77.4	81.8	73.9
1-bit Bonsai 8B (prior)	1.15 GB	70.5	65.7	50	88	73.8	79.8	65.7
RNJ 8B	16.63 GB	73.1	75.5	50.4	93.7	84.2	73.8	61.1
Ministral3 8B	16.04 GB	71.0	68.9	53.8	87.9	72.6	67.4	75.4
Olmo 3 7B	14.60 GB	70.9	72	56.1	92.5	79.3	87.1	38.4

Ternary Bonsai 8B ranks 2nd among all compared models despite being 1/8th the size.

Intelligence Density

density = -ln(1 - score/100) / size_GB

Model	Size	Intelligence Density (1/GB)
Ternary Bonsai 8B	2.18 GB	0.645
1-bit Bonsai 8B (prior)	1.15 GB	1.062
Qwen 3 8B	16.38 GB	0.096
RNJ 8B	16.62 GB	0.079

Citation

@techreport{ternarybonsai,
    title   = {Ternary Bonsai: 1.58-bit Language Models at 8B, 4B, and 1.7B Scale},
    author  = {Prism ML},
    year    = {2026},
    month   = {April},
    url     = {https://prismml.com}
}

Contact

For questions, feedback, or collaboration inquiries: contact@prismml.com

Downloads last month: 23,834

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

16-bit

View +1 variant

Model tree for prism-ml/Ternary-Bonsai-8B-gguf

Base model

prism-ml/Ternary-Bonsai-8B-unpacked

Quantized

(17)

this model

Space using prism-ml/Ternary-Bonsai-8B-gguf 1

Collection including prism-ml/Ternary-Bonsai-8B-gguf

Ternary Bonsai

Collection

1.58-bit Bonsai models • 9 items • Updated Apr 20 • 89

Evaluation results

Gsm8k on openai/gsm8k View evaluation results source leaderboard

91