# Bonsai 27B — first 27B-class LLM to run on a phone at ~4 GB

> Bonsai 27B is the first 27B-class open-weight model small enough to run on a phone — 3.9 GB of weights, 262K context, Apache-2.0.

- Org: PrismML
- Date: 2026-07-14
- Category: model
- Source: https://prismml.com/news/bonsai-27b
- Canonical page: https://ai-tldr.dev/releases/prismml-bonsai-27b/

## In short

Bonsai 27B is a 27.3B open-weight model distilled from Qwen3.6-27B that fits in ~4 GB of RAM on a phone using 1-bit or ternary weights, has a 262K-token context, and keeps 90–95% of the full-precision baseline on a 15-benchmark suite.

## What it is

Bonsai 27B is PrismML's new multimodal flagship: a 27.3B open-weight language model distilled from Qwen3.6-27B and released in ternary and 1-bit quantizations under Apache-2.0. Weights ship as small as 3.9 GB, so the whole 27B parameter count fits in a modern phone's RAM. A vision tower is optional for image inputs, and the context window is 262K tokens.

## How it works

PrismML compresses each of Bonsai 27B's weights to 1.125 effective bits (1-bit) or 1.71 bits (ternary), which is what turns a 27B model into a 3.9–5.9 GB file. The backbone uses hybrid attention (~75% linear, ~25% full) with SwiGLU MLP, RoPE, and RMSNorm, plus custom MLX, CUDA, AWQ, GGUF, and WebGPU kernels so the compressed weights run natively on Apple Silicon, NVIDIA GPUs, and the browser.

## Why it matters

A 27B model that fits in ~4 GB of RAM makes an actual frontier-sized brain runnable on a phone or a laptop, not just a demo. PrismML measures 90–95% of the full-precision baseline on their 15-benchmark suite, so the compression is close to lossless. That closes the gap between what a local model can do and what only a server-hosted model used to.

## Who it's for

mobile devs, edge inference builders, anyone deploying local LLMs

## Try it

huggingface.co/collections/prism-ml/bonsai-27b (MLX / GGUF / AWQ / WebGPU)

## Quick facts

- Maker: PrismML (Caltech spinout)
- License: Apache-2.0
- Base model: Qwen3.6-27B
- Variants: 1-bit (3.9 GB) and ternary 1.71-bit (5.9 GB)
- Context window: 262K tokens
- On-device RAM: ~4 GB (1-bit) / ~6 GB (ternary)
- Hardware: Apple MLX (Mac/iPhone/iPad), NVIDIA CUDA, WebGPU

## FAQ

### How does Bonsai 27B fit on a phone?

Bonsai 27B stores its 27.3B weights at 1.125 or 1.71 effective bits each using PrismML's ternary and 1-bit quantization, cutting the model to 3.9 GB or 5.9 GB on disk. That footprint fits in the ~4–6 GB of RAM a modern phone can spare, so the full 27B parameter count runs locally instead of only in a data-center.

### How much quality does Bonsai 27B lose from quantization?

Across PrismML's 15-benchmark suite in thinking mode, Bonsai 27B ternary retains 95% of the full-precision baseline (80.5 vs 85.0) and the 1-bit variant retains 90% (76.1). The paper positions the trade-off as a 27B-class model at a footprint smaller than most full-precision 2B models.

### How fast is Bonsai 27B on real hardware?

PrismML reports Bonsai 27B at up to 163 tok/s on an NVIDIA RTX 5090 (1-bit) and 134 tok/s ternary, and up to 87 tok/s on an Apple M5 Max (1-bit) with 58 tok/s ternary. Phone throughput is lower but the on-device budget is set by the ~4 GB RAM ceiling, not the FLOPs.

### Where can I download Bonsai 27B?

PrismML publishes Bonsai 27B on Hugging Face in one collection (`prism-ml/bonsai-27b`) with MLX 1-bit, MLX 2-bit ternary, GGUF, AWQ-4bit, and unpacked full-precision variants, all under Apache-2.0. A hosted API is also live at together.ai, and the model runs in-browser through the WebGPU kernels Space.

## Links

- [Announcement](https://prismml.com/news/bonsai-27b)
- [HF Collection](https://huggingface.co/collections/prism-ml/bonsai-27b)
- [Whitepaper (PDF)](https://github.com/PrismML-Eng/Bonsai-demo/blob/main/bonsai-27b-whitepaper.pdf)
- [GitHub Demo](https://github.com/PrismML-Eng/Bonsai-demo)
- [WebGPU Demo](https://huggingface.co/spaces/webml-community/bonsai-webgpu-kernels)