--- license: apache-2.0 library_name: llama.cpp pipeline_tag: text-generation tags: - 1-bit - gguf - llama-cpp - cuda - metal - 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-GGUF-1bit End-to-end 1-bit language model for llama.cpp (CUDA, Metal, CPU) > **13.9x** smaller than FP16 | **3.0x** faster on RTX 4090 | runs on any device ## Highlights - Deployed footprint — runs on virtually any device - **End-to-end 1-bit weights** across embeddings, attention projections, MLP projections, and LM head - **GGUF Q1_0 (g128)** format for 1-bit packing of weights with shared scales for each group (group size 128). - **Cross-platform**: CUDA (RTX/datacenter), Metal (Mac), Swift (iPhone/iPad), Android - **MLX companion**: also available as [MLX 1-bit g128](https://huggingface.co/prism-ml/Bonsai-1.7B-mlx-1bit) for native Apple Silicon inference

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**: [llama.cpp fork](https://github.com/PrismML-Eng/llama.cpp) (CUDA + Metal) · [MLX fork](https://github.com/PrismML-Eng/mlx) (Apple Silicon) · [mlx-swift fork](https://github.com/PrismML-Eng/mlx-swift) (iOS/macOS) - **[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 | GGUF Q1_0 | | Deployed size | **0.24 GB** (14.2x smaller than FP16) | | 1-bit coverage | Embeddings, attention projections, MLP projections, LM head | | License | Apache 2.0 | ## Quantization Format: Q1_0 Each weight is a single bit: `0` maps to `−scale`, `1` maps to `+scale`. Every group of 128 weights shares one FP16 scale factor. Effective bits per weight: **1.125** (1 sign bit + 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 | | **GGUF Q1_0 ** | **0.24 GB** | **93.0%** | **14.2x** | | MLX 1-bit g128 | 0.27 GB | 92.2% | 12.8x | The GGUF file on disk is 0.25 GB (~6.2 MB larger) because the format embeds the tokenizer, chat template, and model metadata 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 ### llama.cpp (CUDA) ```bash # Clone the PrismML fork of llama.cpp (includes Q1_0 kernels) git clone https://github.com/PrismML-Eng/llama.cpp cd llama.cpp # Build with CUDA support cmake -B build -DGGML_CUDA=ON && cmake --build build -j # Run inference ./build/bin/llama-cli \ -m Bonsai-1.7B-Q1_0.gguf \ -p "Explain quantum computing in simple terms." \ -n 256 \ --temp 0.5 \ --top-p 0.85 \ --top-k 20 \ -ngl 99 ``` ### llama.cpp (Metal / macOS) ```bash # Clone the PrismML fork of llama.cpp (includes Q1_0 kernels) git clone https://github.com/PrismML-Eng/llama.cpp cd llama.cpp # Build with Metal support (default on macOS) cmake -B build && cmake --build build -j # Run inference ./build/bin/llama-cli \ -m Bonsai-1.7B-Q1_0.gguf \ -p "Explain quantum computing in simple terms." \ -n 256 \ --temp 0.5 \ --top-p 0.85 \ --top-k 20 \ -ngl 99 ``` ### llama.cpp Server ```bash ./build/bin/llama-server \ -m Bonsai-1.7B-Q1_0.gguf \ --host 0.0.0.0 \ --port 8080 \ -ngl 99 ``` Open the web UI at [http://127.0.0.1:8080](http://127.0.0.1:8080), or see our [llama.cpp fork](https://github.com/PrismML-Eng/llama.cpp) for more examples. ## Cross-Platform Throughput | Platform | Backend | TG128 (tok/s) | FP16 TG (tok/s) | TG vs FP16 | PP512 (tok/s) | FP16 PP512 (tok/s) | | :----------- | :-------------- | ------------: | --------------: | ---------: | ------------: | -----------------: | | RTX 4090 | llama.cpp CUDA | 674 | 224 | **3.0x** | 31,899 | 30,630 | | M4 Pro 48 GB | llama.cpp Metal | 250 | 65 | **3.8x** | 2,305 | 2,291 | ## 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**