Open Source
Bonsai 2 and Needle: Tiny Local AI Models
Lev Selectorhigh confidence
Why it matters
- →Enables offline, private AI usage.
- →Reduces infrastructure costs significantly.
- →Demonstrates efficiency gains in model design.
Developers have released Bonsai 2 and Needle, two extremely lightweight AI models weighing only 8-29 MB. These models are designed for offline action and local deployment, proving that small parameter counts can still deliver high utility for specific tasks. They enable real-time decision-making without cloud dependency, reducing latency and privacy concerns. This trend highlights the growing viability of edge AI for everyday applications.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Local AI Models Gain Traction for Everyday Tasks
Matt Wolfe · June 11, 2026 · Related
- 2Local Models Triage OpenClaw Repo for Free
Hugging Face Blog · June 22, 2026 · Background
- 3MiniCPM5: A 1B Model for On-Device Projects
Sam Witteveen · July 5, 2026 · Background
- 4Cactus Needle: 26M Parameter Model Outperforms Larger Rivals
Sam Witteveen · July 12, 2026 · Related
- 5Thinking Machines Lab Releases Inkling Model
WIRED AI · July 15, 2026 · Background
- 6Thinking Machines releases Inkling model
Fireship · July 20, 2026 · Background
- 7PrismML compresses LLMs to run locally with minimal loss
TechCrunch AI · September 17, 2026 · Background
- 8Guide to Running Local AI Models Offline
Lev Selector · September 20, 2026 · Related
What happened next
- 9Strands Launches Decider 2B Agent Model
Matt Wolfe · October 2, 2026 · Background
- 10llama.cpp adds Prism Bonsai 2 27B support
llama.cpp Releases · October 12, 2026 · Background
- 11Apple Releases 20B On-Device Model in Just 2 GB
Lev Selector · October 30, 2026 · Background
- 12Tether AI launches BotPsy, a sub-billion agentic model
Hugging Face Blog · November 11, 2026 · Background
More in Open Source
© Hugging Face BlogOpen Sourceagents
Tether AI launches BotPsy, a sub-billion agentic model
Tether AI Research has released BotPsy, an 0.8B-parameter model built on Qwen3.5 that specializes in tool-use and agentic workflows for on-device deployment. It achieves state-of-the-art performance in its size class, outperforming larger models like Qwen3.5-2B-Think on benchmarks such as BFCL v4 and ACEBench while maintaining strict privacy by keeping data local. The model is designed to handle routine tasks like calendar management and web search without relying on expensive cloud APIs, offering a viable path for private, self-hosted personal assistants. With open weights under Apache 2.0 and GGUF support, it provides immediate utility for developers building lightweight, autonomous agents.
Hugging Face Blog
© Hugging Face BlogOpen Sourceother
NVIDIA releases 9M synthetic Japanese finance personas
NVIDIA has released a massive synthetic dataset of 9 million Japanese financial personas, addressing the privacy and data scarcity bottlenecks in localizing AI for Japan. By grounding these profiles in official government statistics rather than real customer records, it allows developers to train and red-team agents without violating strict privacy regulations. The inclusion of specific attributes like household assets and financial literacy provides a level of demographic granularity that generic Western-centric datasets simply cannot match. This effectively lowers the barrier for building culturally accurate, compliant AI systems in one of the world's largest economies.
Hugging Face Blog
© Matt WolfeOpen Sourceimage
Pruna Releases PH3 Image Open-Weight Model
Pruna has released PH3 Image, an open-weight image generation model available on Hugging Face with specific hardware requirements.
Matt Wolfe