PrismML launch from stealth... an AI lab with Caltech origins that is centered on building the most concentrated form of intelligence. teapaw.org/PrismML/status/2039049…
Today, we are emerging from stealth and launching PrismML, an AI lab with Caltech origins that is centered on building the most concentrated form of intelligence.
At PrismML, we believe that the next major leaps in AI will be driven by order-of-magnitude improvements in intelligence density, not just sheer parameter count.
Our first proof point is the 1-bit Bonsai 8B, a 1-bit weight model that fits into 1.15 GBs of memory and delivers over 10x the intelligence density of its full-precision counterparts. It is 14x smaller, 8x faster, and 5x more energy efficient on edge hardware while remaining competitive with other models in its parameter-class.
We are open-sourcing the model under Apache 2.0 license, along with Bonsai 4B and 1.7B models.
When advanced models become small, fast, and efficient enough to run locally, the design space for AI changes immediately. We believe in a future of on-device agents, real-time robotics, offline intelligence and entirely new products that were previously impossible.
We are excited to share our vision with you and keep working in the future to push the frontier of intelligence to the edge.
11
Today, we are emerging from stealth and launching PrismML, an AI lab with Caltech origins that is centered on building the most concentrated form of intelligence.
At PrismML, we believe that the next major leaps in AI will be driven by order-of-magnitude improvements in intelligence density, not just sheer parameter count.
Our first proof point is the 1-bit Bonsai 8B, a 1-bit weight model that fits into 1.15 GBs of memory and delivers over 10x the intelligence density of its full-precision counterparts. It is 14x smaller, 8x faster, and 5x more energy efficient on edge hardware while remaining competitive with other models in its parameter-class.
We are open-sourcing the model under Apache 2.0 license, along with Bonsai 4B and 1.7B models.
When advanced models become small, fast, and efficient enough to run locally, the design space for AI changes immediately. We believe in a future of on-device agents, real-time robotics, offline intelligence and entirely new products that were previously impossible.
We are excited to share our vision with you and keep working in the future to push the frontier of intelligence to the edge.
Today we’re announcing Ternary Bonsai: Top intelligence at 1.58 bits
Using ternary weights {-1, 0, +1}, we built a family of models that are 9x smaller than their 16-bit counterparts while outperforming most models in their respective parameter classes on standard benchmarks.
We’re open-sourcing the models under the Apache 2.0 license in three sizes: 8B (1.75 GB), 4B (0.86 GB), and 1.7B (0.37 GB).
Today, we’re announcing Bonsai 27B: the first 27B-class model to run on a phone.
Bonsai 27B is the new multimodal flagship of the Bonsai family. Based on Qwen3.6 27B, it brings a new capability tier to local AI: multi-step reasoning, structured tool use, long-context workflows, and coherent agentic loops.
Until now, models in this class have been impractical to deploy locally. A 27B model occupies roughly 54 GB in 16-bit precision, and even a strong 4-bit build is around 18GB - too large for a phone and for most laptops.
Bonsai 27B changes that.
It comes in two variants:
• Ternary Bonsai 27B: 5.9 GB, 1.71 effective bits per weight, optimized for laptop-class quality.
• 1-bit Bonsai 27B: 3.9 GB, 1.125 effective bits per weight, optimized for phone-class footprint.
Everything is open-sourced today under the Apache 2.0 license.
Read the full announcement: prismml.com/news/prismml-bri…
Today at Snapdragon Summit, we’re announcing 1-bit Bonsai vision-language model running locally on AI smart glasses powered by Snapdragon® AR1 Gen 1 Platform.
With Qualcomm Technologies, we optimized Bonsai for Snapdragon Hexagon™ NPU, delivering 4x lower memory usage and 2x faster token generation for equivalent intelligence, making it possible to bring significantly more capable AI to run directly on highly constrained wearable devices.
We believe model-hardware co-design will be critical to bringing increasingly capable AI from the cloud onto the devices people use every day.
Today, we’re releasing Bonsai 2 2B, 4B, and 9B.
Based on Qwen3.5, these new ternary models bring stronger reasoning, visual understanding, and tool calling to compact footprints designed for everyday devices:
• 2B: 0.43GB
• 4B: 0.95GB
• 9B: 2.0GB
For this release, we focused on what makes small models useful as local assistants: following instructions, avoiding repetitive loops, calling tools on mobile devices, and giving useful answers without unnecessary output. The 9B model uses roughly 40% fewer tokens on standard instruction-following and everyday math tasks. Solving the Riemann hypothesis can wait.
These models are successors to our first-generation Bonsai 1.7B, 4B, and 8B, and provide a foundation for bringing practical agentic functionality to local applications on personal computers, phones, and wearables.
The Bonsai 2 family now includes four sizes spanning 2B to 27B parameters. Developers can choose the balance of capability, memory use, and responsiveness that fits their application and hardware.
Available today under Apache 2.0.
FortyThree PR retweeted
BTD Capital Fund (ticker: DIP) is a venture into a simple strategy applied proficiently and efficiently. It’s machine learning-based technology powering an actively managed ETF. Learn more: zcu.io/InV3
#AI #stocks #finance #FinTech
Good luck to one of our Account Managers @DavidHayflee at this weekend's 8th annual TAC Skim Blast. Congratulations on your hard work in helping to organize the event, too! 🏄
More about the event @scsentinel :
santacruzsentinel.com/2022/0…
Congratulations to one of our valued Account Managers, @laurenchouinard, on her hard work and dedication in the role of Jan in the Cabrillo Stage Production of GREASE: The Musical!
Lauren was mentioned in The Aptos Times!
#theatre #Greasethemusical #Aptostimes #CabrilloStage
Metagaia: Blockchain Metaverse Video sknr.net/2022/06/15/metagaia…
FortyThree PR retweeted
EXCLUSIVE: Survey Suggests Investors Losing Touch With Market, Trust Algorithmic Alternatives
benzinga.com/markets/22/04/2…
$SPY $QQQ $DIA $IWM
You should check out @Meta_Gaia, They are building a multi-game play-to-earn metaverse, and their first game is called HexaHero...think Axie Infinity, but with battle robots in outer space. Check it out!
1
Boosting economic and social prosperity is a lofty goal, but in our article we posit that better access to mass transportation could bring widespread shared prosperity for the working and middle classes. Read more at: kcm.vg/insights/disseminate-…
Leslie Kelly @lesliedines at Forbes @Forbes spoke with co-founder, VP and second-generation Alaskan fisherman, Marsh Skeele at Sitka Salmon Shares @SitkaShares on its community-supported fishery (CSF) centered around its small-boat fishermen.
Kelly has some experience working on a fishing vessel herself! Check out the finer details of how the company brings perfect fish from the waters of Alaska to the lower 48.
forbes.com/sites/lesliekelly…
NextNav can figure out which floor you’re on in a skyscraper venturebeat.com/2020/07/17/n… via @VentureBeat















