--- license: apache-2.0 library_name: mlx pipeline_tag: text-generation tags: - 1-bit - mlx - apple-silicon - on-device - prismml - bonsai base_model: - prism-ml/Bonsai-1.7B-unpacked ---

Bonsai

Prism ML Website  |  Whitepaper  |  Demo & Examples  |  Colab Notebook  |  Discord

# Bonsai-1.7B-mlx-1bit End-to-end 1-bit language model for Apple Silicon > **12.8x** smaller than FP16 | **4.6x** faster on M4 Pro | **130** tok/s on iPhone | runs on Mac, iPhone, iPad ## Highlights - Deployed footprint — runs on virtually any Apple device - **End-to-end 1-bit weights** across embeddings, attention projections, MLP projections, and LM head - **MLX-native format** (1-bit g128) with inline dequantization kernels — no FP16 materialization - **Cross-platform companion**: also available as [GGUF Q1_0_g128](https://huggingface.co/prism-ml/Bonsai-1.7B-gguf) for llama.cpp

Frontier Efficiency

## Resources - **[Google Colab](https://colab.research.google.com/drive/1EzyAaQ2nwDv_1X0jaC5XiVC3ZREg9bdG?usp=sharing)** — try Bonsai in your browser, no setup required - **[Whitepaper](https://github.com/PrismML-Eng/Bonsai-demo/blob/main/1-bit-bonsai-8b-whitepaper.pdf)** — for more details on Bonsai, check out our whitepaper - **[Demo repo](https://github.com/PrismML-Eng/Bonsai-demo)** — comprehensive examples for serving, benchmarking, and integrating Bonsai - **[Discord](https://discord.gg/prismml)** — join the community for support, discussion, and updates - **1-bit kernels**: [MLX fork](https://github.com/PrismML-Eng/mlx) (Apple Silicon) · [mlx-swift fork](https://github.com/PrismML-Eng/mlx-swift) (iOS/macOS) · [llama.cpp fork](https://github.com/PrismML-Eng/llama.cpp) (CUDA + Metal) - **[Locally AI](https://locallyai.app/)** — we have partnered with Locally AI for iPhone support ## Model Overview | Item | Specification | | :------------- | :----------------------------------------------------------------------- | | Parameters | 1.7B (~1.4B non-embedding) | | Architecture | Qwen3-1.7B dense: GQA (16 query / 8 KV heads), SwiGLU MLP, RoPE, RMSNorm | | Layers | 28 Transformer decoder blocks | | Context length | 32,768 tokens | | Vocab size | 151,936 | | Weight format | MLX 1-bit g128 | | Deployed size | **0.27 GB** (12.8x smaller than FP16) | | 1-bit coverage | Embeddings, attention projections, MLP projections, LM head | | License | Apache 2.0 | ## Quantization Format: 1-bit g128 Each weight is a single bit: `0` maps to `−scale`, `1` maps to `+scale`. Every group of 128 weights shares one FP16 scale factor. MLX's quantization formats generally store both a scale and a bias per group: `w = mlx_scale * bit + mlx_bias`. To pack our scale-only 1-bit weights into this format: ``` mlx_scale = 2 * original_scale mlx_bias = −original_scale ``` This reconstructs `−scale` when `bit=0` and `+scale` when `bit=1`. Because MLX stores two FP16 values per group (scale + bias) instead of one, the effective bits per weight is slightly higher than the GGUF format: - **MLX 1-bit g128**: **1.25 bpw** (1 sign bit + two 16-bit values amortized over 128 weights) - **GGUF Q1_0_g128**: **1.125 bpw** (1 sign bit + one 16-bit scale amortized over 128 weights) ### Memory Requirement Parameter memory only (weights and scales loaded into memory): | Format | Size | Reduction | Ratio | | :----------------- | ----------: | --------: | --------: | | FP16 | 3.44 GB | — | 1.0x | | **MLX 1-bit g128** | **0.27 GB** | **92.2%** | **12.8x** | | GGUF Q1_0_g128 | 0.24 GB | 93.0% | 14.2x | The model directory on disk is ~0.28 GB (~16 MB larger) because it also includes tokenizer, config, and other metadata files alongside the weights. ## Best Practices ### Generation Parameters | Parameter | Default | Suggested range | | :----------------- | :------ | :-------------- | | Temperature | 0.5 | 0.5 -- 0.7 | | Top-k | 20 | 20 -- 40 | | Top-p | 0.9 | 0.85 -- 0.95 | | Repetition penalty | 1.0 | | | Presence penalty | 0.0 | | ### System Prompt You can use a simple system prompt such as: ``` You are a helpful assistant ``` ## Quickstart ### MLX (Python) > **Requires PrismML fork of MLX** with 1-bit kernel support (upstream PR pending): > ```bash > pip install mlx-lm > pip install mlx @ git+https://github.com/PrismML-Eng/mlx.git@prism > ``` ```python from mlx_lm import load, generate model, tokenizer = load("prism-ml/Bonsai-1.7B-mlx-1bit") response = generate( model, tokenizer, prompt="Explain quantum computing in simple terms.", max_tokens=256, ) print(response) ``` ### MLX Swift (iOS / macOS) 1-bit Bonsai 1.7B runs natively on iPhone and iPad via MLX Swift. Requires our [mlx-swift fork with 1-bit kernels](https://github.com/PrismML-Eng/mlx-swift) (upstream PR pending). ## Throughput (MLX / Apple Silicon) | Platform | Backend | TG128 (tok/s) | FP16 TG (tok/s) | TG vs FP16 | PP512 (tok/s) | FP16 PP512 (tok/s) | | :---------------- | :-------------- | ------------: | --------------: | ---------: | ------------: | -----------------: | | M4 Pro 48 GB | MLX (Python) | 288 | 62 | **4.6x** | 1,759 | 1,585 | | M4 Pro 48 GB | llama.cpp Metal | 250 | 65 | **3.8x** | 2,305 | 2,291 | | iPhone 17 Pro Max | MLX Swift | 130 | — | — | 1,523 | — | ## Citation If you use 1-bit Bonsai 1.7B, please cite: ```bibtex @techreport{bonsai, title = {Bonsai: End-to-End 1-bit Language Model Deployment Across Apple, GPU, and Mobile Runtimes}, author = {Prism ML}, year = {2026}, month = {March}, url = {https://prismml.com} } ``` ## Contact For questions, feedback, or collaboration inquiries: **contact@prismml.com**