Ternary-Bonsai-4B-mlx-2bit

<p align="center"> <img src="./assets/bonsai-logo.svg" width="280" alt="Bonsai"> </p> <p align="center"> <a href="https://prismml.com"><b>Prism ML Website</b></a> &nbsp;|&nbsp; <a href="https://github.com/PrismML-Eng/Bonsai-demo/blob/main/ternary-bonsai-8b-whitepaper.pdf"><b>White Paper</b></a> &nbsp;|&nbsp; <a href="https://github.com/PrismML-Eng/Bonsai-demo"><b>Demo &amp; Examples</b></a> &nbsp;|&nbsp; <a href="https://discord.gg/prismml"><b>Discord</b></a> </p>

Ternary-Bonsai-4B-mlx-2bit

Ternary (1.58-bit) language model for Apple Silicon

7.1x smaller than FP16 | 4.8x faster on M4 Pro | 50 tok/s on iPhone | runs on Mac, iPhone, iPad

Highlights

• 1.05 GiB (1.13 GB) packed 2-bit size (down from 8.04 GB FP16) — runs on any Mac or iPhone
• Ternary weights {-1, 0, +1} across embeddings, attention projections, MLP projections, and LM head
• 70.7 avg benchmark score across 6 categories — competitive with full-precision 4B models
• MLX-native format with group size 128 and FP16 scaling

<p align="center"> <img src="./assets/frontier.svg" width="680" alt="Pareto Frontier"> </p>

Resources

• White Paper
• Demo repo — examples for serving, benchmarking, and integrating Bonsai
• Discord — community support and updates
• Kernels: MLX (Apple Silicon) · mlx-swift (iOS/macOS) — 2-bit format is supported out of the box

Model Overview

Quantization Format: Ternary 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}

The information-theoretic cost is log2(3) ≈ 1.585 bits per weight, plus FP16 group scales (16 bits per 128 weights), for a theoretical minimum of ~1.71 bits/weight. This release uses the MLX 2-bit format, which stores each ternary value in 2 bits plus group scales, for an effective ~2.125 bits/weight.

Memory

Quickstart

MLX (Python)

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("prism-ml/Ternary-Bonsai-4B-mlx-2bit")

response = generate(
    model,
    tokenizer,
    prompt="Explain quantum computing in simple terms.",
    max_tokens=256,
)
print(response)

Throughput (MLX / Apple Silicon)

iPhone 17 Pro Max (MLX Swift)

Benchmarks

Evaluated with EvalScope v1.4.2 + vLLM 0.15.1 on NVIDIA H100. Full benchmark suite (10 benchmarks):

Intelligence Density

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

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: [email protected]