PrismML has released Bonsai 27B, an AI model that runs on a smartphone without losing reasoning or agent capabilities. Apple is reportedly testing the technology.
The company, founded by former Caltech researchers, built the 27-billion-parameter model based on Alibaba’s Qwen3.6-27B. It supports multistep reasoning, tool use, image understanding, and agent-based tasks.
PrismML argues that modern AI apps increasingly need powerful models to run locally. An agent may make hundreds of model calls in sequence, each carrying context, producing structured output, and feeding into the next step. In the cloud, per-token costs pile up, every call adds network latency, and intermediate results, tool calls, and private data such as screen content or documents all leave the device.
But running the model on-device cuts the marginal cost of those loops to zero and keeps user data local. PrismML sees this as the basis for always-on agents, offline assistants, and hybrid systems. Simple and privacy-sensitive tasks stay on-device, while only the hardest steps are sent to frontier models in the cloud.
According to a CNBC report, PrismML is already in talks with Apple about the compression technology behind Bonsai. PrismML CEO Babak Hassibi confirmed that Apple and other companies are testing the models for speed, power draw, and performance. The talks are “very early,” but “things are progressing nicely.”
Two versions bring the model to laptops and smartphones
A model this size typically takes up about 54 GB of storage. Even with standard compression, it still needs around 18 GB. PrismML offers two much smaller versions: The quality-focused variant takes up about 5.9 GB and is meant for laptops, though the packages currently shipping may be larger depending on the runtime. The white paper lists about 7.2 GB for the llama.cpp version and 8.49 GB for the MLX version.
The smaller variant comes in at about 3.9 GB, small enough to fit within the limited storage of an iPhone 17 Pro Max. According to PrismML, an iPhone with 12 GB of RAM actually makes only about 6 GB available to a single app, split between the model and the cache.
Instead of storing each neural network weight as 16 bits, PrismML uses only one or just under two bits. In the most aggressive variant, each weight has only two states. In the slightly larger one, three. This approach is applied across the entire language model. As an example of common labeling issues, PrismML points to the Qwen3.6-27B-IQ2_XXS build compared in the white paper, which averages 2.8 bits per weight despite its “2-bit” label.
PrismML says compression has a limited impact on quality
In PrismML’s own evaluation across 15 benchmarks, the larger variant keeps 95 percent of the original model’s performance. The smaller one keeps 90 percent. Math and coding stayed “virtually unaffected,” according to PrismML.
The bigger drops showed up with the more aggressive compression, especially in image understanding, instruction following, and agent-based tool use. A conventionally compressed Qwen3.6-27B model at 9.4 GB scores only 72.7 points, while the smaller Bonsai variant at 3.9 GB scores 76.1.
According to the white paper, the smaller variant generates about 11 tokens per second on an iPhone 17 Pro Max. A battery test yielded roughly 672 generated tokens per percentage point of battery charge, which extrapolates to about 67,000 tokens on a full charge. The chip throttled slightly after a little over five minutes.
Apple could use the tech to close its local AI gap
The model weights are available under the Apache 2.0 license. Bonsai 27B runs on Apple devices via Apple’s MLX framework and on NVIDIA GPUs. PrismML also provides a time-limited, free Developer Preview API and a live demo on HuggingFace.
The company was founded with backing from Khosla Ventures, Cerberus, and Google, and Samsung continues to support it. PrismML plans to apply its compression tech to Google’s Gemma model series next, smaller versions of which already run on smartphones.
A licensed compression technology would also matter to Apple, whose own models have trailed the competition in benchmarks so far. At WWDC 2026, Apple unveiled a revamped Siri built on foundation models developed with Google using Gemini technology. The most powerful on-device model already requires an iPhone with at least 12 GB of RAM, and complex queries run on Nvidia GPUs in Apple’s cloud.
What it means
Developers and power users now have a way to run complex logic locally without paying per token or risking data leaks. The model runs on existing hardware, though the aggressive compression limits speed and battery life. Apple appears interested in adopting similar techniques to improve its own on-device capabilities.
