https://prismml.com/ [6996184773] About News Careers Contact [69954d0b2a][69954d0be5] Now hiring Explore open roles at Prism^ML Concentrating intelligence Large models can't fit on smartphones. Datacenters can't sustain them. Prism^ML is building ultra dense intelligence to solve both. Launch announcement [69954ccfb1] 14x less memory [69c7280f8b] 8x faster [69954cd6bf] 5x less energy 1-bit Bonsai 8B [69c94de785] 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 14x smaller footprint than a full-precision 8B model, runs 8x faster, and is 5x more energy efficient, while matching leading 8B models on benchmarks. This results in over 10x the intelligence density of full-precision 8B models1. Download model 1-bit Bonsai 4B [69c94de785] 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 [69c94de785] 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: [69a70d266b] [69973e742b] [69973e0365] [69973e74d0] Supported by: [6988ec2b48][6988ec2b5d][698d6a6fde][6988ec2ba3] Benchmark palette Intelligence density Bonsai 8B canopy Performance vs. size Benchmarks Throughput Energy consumption 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) Benchmark - [] - 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, Prism^ML 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 [699f8de594] Pasadena or San Francisco [699f8de5dc] Full-time See details Staff AI/ML Engineer - Edge & Consumer AI [699f8de594] Pasadena or San Francisco [699f8de5dc] Full-time See details [6996184773] About Careers Contact (c) 2026 Prism ML, Inc. All rights reserved. Terms & Conditions Privacy Policy [69954d0b2a][69954d0be5] Join the team [6994cf1a7b] [Select role... ][ ] [ ][ ] Resume: [ ] Upload File Max file size 10MB. Uploading... fileuploaded.jpg Upload failed. Max size for files is 10 MB. [ ] [Submit application] Thanks, your application has been received! Oops! Something went wrong while submitting the form. Contact us [6994cf1a7b] Have a question, partnership idea, or a project that needs efficient intelligence? Reach out--we'd love to hear from you. [ ][ ][ ] [ ] [Send message] Thanks, your message has been received! Oops! Something went wrong while submitting the form.