Actively hiring
Multimodal AI
Edge AI
Foundation Models
As featured in
Follow
Overview
News
Salaries
Products
People
Growth
Offices
Financials
Funding and backers
Team
11-50
employees, estimated range
Backers
1
Khosla Ventures
Momentum
0/100
no fresh signals
Last sign of life
1 mo ago
a posting or a news item
The story so fareach stage dated by its source: the company's releases, the press, registers, filings
Sep 17
On the Hacker News front page Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint · 589 points
Jul 14
On the Hacker News front page Bonsai 27B: A 27B-Class model that runs on a phone · 706 points
May 26
Released an app Bonsai Studio by PrismML · App Store
Apr 18
On the Hacker News front page Ternary Bonsai: Top Intelligence at 1.58 Bits · 225 points
Apr 2
Launched PrismML Introduces Ternary Bonsai Model Family · morningstar.com
Apr 13, 2025
Released an app Locally AI by LM Studio · App Store
Tractionpublic signals, read monthly
Web presence
top 2%
of 133.2M domains by links, Common Crawl
App Store
4.7 ★
1.8k ratings
Backed byfrom the funds' portfolios and accelerator catalogs
Investors in similar startupsfunds that back the companies most like this one
Similar startupsby what they do, their industry and backers

AGI7 is building the future of Physical AI with agentic intelligence, edge AI, multimodal perception, and autonomous systems for real-world…

LTX builds open-weight diffusion transformer foundation models for multimodal video, audio, and world simulation.

ModelBest is a Chinese artificial intelligence company founded in 2022 with roots in Tsinghua University research on large models. It…

Onesight Technology helps teams bring BIM into site workflows with AR and turn structured site imagery into management information with…

Thinking Machines Lab is an artificial intelligence research and product company based in San Francisco and founded in 2025. The company…

Mirai Labs builds uzu, a Rust LLM engine for iPhone, iPad and Mac, and 4-bit/8-bit Qwen, LFM and Muse-Glimmer models benchmarked vs MLX and…
News
Apple Tests PrismML for More Powerful iPhone AI
Apple is testing PrismML technology that could run larger AI models directly on future iPhones, improving speed, privacy, and offline access for users.
Read more
Report
27 Billion Parameters on an iPhone: Why Apple's On-Device AI Changes Everything
How can a 27-billion-parameter AI model run on an iPhone? Explore model compression, on-device AI, Apple Intelligence, privacy, and why Apple's strategy could reshape enterprise AI.
Read more
Report
PrismML confirms it is in talks with Apple about AI model-shrinking tech
Five days after initial reports that there was an AI-model shrinking technology by PrismML suitable for iPhones, the company has confirmed it is talking to Apple over the use of its technology.
Read more
Report
Apple in talks with startup that shrinks AI models to run on an iPhone
PrismML says its compressed version of Alibaba's Qwen model uses up to 15 times less memory, potentially advancing Apple's AI push.
Read more
Report
Apple is indeed evaluating PrismML's technology, for shrinking AI models - MacTech.com
On July 10, it was reported by Seeking Alpha thatPrismML has compressed Alibaba's open-source Qwen 3.6 large language model to run on the iPhone 17 Pro. This has been confirmed. CNBC reports that Apple is indeed evaluating PrismML's technology, which the
Read more
Report
PrismML - Announcing Bonsai 27B: The First 27B-Class Model to Run on a Phone
Today we're announcing Bonsai 27B, our multimodal flagship: ternary at 5.9GB for laptops, 1-bit at 3.9GB for an iPhone 17 Pro, with a 262K-token context.
Read more
Report
Apple talks with startup that could cram GPT-class AI onto your iPhone
Apple is reportedly talking to a startup that claims it squeezed a massive AI language model onto an iPhone.
Read more
Report
Market Chatter: PrismML Runs 27-Billion-Parameter AI Model on iPhone
Startup PrismML has gotten an artificial intelligence model running on an Apple (AAPL) iPhone 17 Pro
Read more
Report
PrismML - Introducing 1-bit and Ternary Bonsai Image 4B: Image Generation for Local Devices
Today we're releasing Bonsai Image 4B, compact 1-bit and ternary diffusion models built on FLUX.2 Klein 4B that run image generation on laptops and phones.
Read more
Report
Show more news

Khosla Ventures 




