Concentrating intelligence

Large models can't fit on smartphones. Datacenters can't sustain them. PrismML is building ultra dense intelligence to solve both.
Launch announcement
14× less memory
8× faster
5× less energy

1-bit Bonsai 8B

The first commercially viable model with 1-bit weights. Requiring only 1.15GB of memory, 1-bit Bonsai 8B was engineered for robotics, real-time agents, and edge computing. It has a 14× smaller footprint than a full-precision 8B model, runs 8× faster, and is 5× more energy efficient, while matching leading 8B models on benchmarks. This results in over 10× the intelligence density of full-precision 8B models¹.

Download model

1-bit Bonsai 4B

Requiring just 0.57GB of memory, 1-bit Bonsai 4B delivers exceptional speed, reaching 132 tokens per second on an M4 Pro. It pairs strong accuracy with outstanding energy efficiency, making it ideal for workloads that demand both performance and speed¹.

Download model

1-bit Bonsai 1.7B

With a footprint of only 0.24GB of memory, 1-bit Bonsai 1.7B pushes the limits of on-device speed, reaching 130 tokens per second on an iPhone 17 Pro Max. Combining industry-leading energy efficiency with solid accuracy, it’s a lightweight model built for heavyweight tasks¹.

Download model
Supported by:
Benchmark palette

Intelligence density

Negative log of the model's error rate divided by the model size

For detailed evaluation approach, please refer to our whitepaper.

Model benchmark comparison

Average score (IFEval, GSM8K, HumanEval+, BFCL, MuSR, MMLU-Redux)

For detailed evaluation approach, please refer to our whitepaper.

Throughput

Tokens per second across hardware platforms (higher is better)

For detailed evaluation approach, please refer to our whitepaper.

Performance vs. size

Average score (IFEval, GSM8K, HumanEval+, BFCL, MuSR, MMLU-Redux)

For detailed evaluation approach, please refer to our whitepaper.

Bonsai 8B canopy

Average score (IFEval, GSM8K, HumanEval+, BFCL, MuSR, MMLU-Redux)

For detailed evaluation approach, please refer to our whitepaper.

Energy consumption

Milliwatt-hours per token across hardware (lower is better)

For detailed evaluation approach, please refer to our whitepaper.
16.0 GB 16-bit (standard)

1-bit Bonsai 8B

Centering AI research on efficiency

Successful artificial intelligence isn’t just about making models larger, but also smarter. Utilizing breakthrough research at Caltech, PrismML is pushing the frontier of intelligence density by reshaping how models are designed, prioritizing intelligence per bit over sheer parameter count.
Get started

Join the team

We are looking for engineers looking to push the frontier of intelligence density.

Staff AI/ML Engineer – Large-Scale Systems

Pasadena or San Francisco
Full-time
See details

Staff AI/ML Engineer – Edge & Consumer AI

Pasadena or San Francisco
Full-time
See details