Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
In plain words
Needle 2 is an open-source 45-parameter language model compressed to 14MB that performs tool calling, device control, and structured data extraction. Designed for resource-constrained devices like phones, smartwatches, smart home systems, and robots, it runs full sessions in 28MB of RAM. The model achieves competitive performance on mobile benchmarks while being significantly smaller than comparable alternatives, delivering 500 tokens per second on a Raspberry Pi 5 and 300-1,500 tokens per second across various consumer devices.
written from the facts on this page · September 2026
From the sources
An open 45M-parameter model for tool calling, device use, and structured extraction. Needle 2 runs as a 14 MB binary in 28 MB of session RAM.
An open 14MB model for tool calling, device use, and structured extraction. Today we release Needle 2: an open 45M-parameter model for tool calling, device use and structured extraction. The whole model is a single 14MB binary that runs in 28MB of RAM. It is built on our Simple Attention Network , compressed to CQ2-bit with Cactus Quants , and baked into its own engine. On the tool call and mobile device use benchmarks, Needle 2 trades wins with other small models like FunctionGemma 270M, LFM2.5 230M and Apple FM, despite being 5× to 70× smaller, and running at 2 bits against their f16. Needle reaches: With a peak session RAM around 28MB, Needle runs on newer microcontrollers like ESP32-S3.…from cactuscompute.com
In the maker’s words, at launch
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300-700 on sub-$200 phones such as the Samsung A-Series. On the tool call and mobile device use benchmarks, Needle 2 trades wins with closest small models like LFM2.5 230M and Apple Foundation Model, at 5x to 70x smaller, both at f16 vs Needle 2 at 2bit. Needle is based on Simple Attention Networks from our paper (https://arxiv.org/abs/2607.18363). Edge AI has lately meant Macs and PCs, but that is just 1.5 billion of over 21 billion connected IoT devices in the world today, and in emerging markets most phones ship under $200, no NPU, cheap GPUs. These include budget phones, Raspberry Pis, microcontrollers, wearables, small robots like Reachy Mini, and connected home devices. A conventional transformer of Needle's width and depth spends 164 MFLOPs per token, and even one squeezed down to Needle's parameter count spends 87, Needle spends 70. Even on a high-end phone, an always-on assistant lives inside a power budget; every MFLOP is milliwatt-hours, and Needle spends 7x to 85x fewer of them per token than the smallest performant LLMs. More about the architecture in the link. When we structure intelligence for consumer devices as functions with typed parameters, the only hard part is mapping a messy sentence onto them; which function, with which values. Our research found that when framed that way, the problem needs no world knowledge and no open-ended prose, which is why 45M parameters suffice. Needle 2 expands to structured extraction where the schema can be passed in-place of tools and the model returns structured output. You can use Needle as a text-classification model with an enum field, as a summarization model by providing a schema that extracts key fields, everything but free-range decode. Every product has its own tool vocabulary and fine-tuning needle helps it achieve frontier-level performance on custom tasks, so using the python package (https://github.com/cactus-compute/needle), Needle can be fine-tuned Needle on a Mac/PC in minutes to a few hours, with automated data-generation pipeline, just pass a couple samples. Nonetheless, every response carries a learned confidence score based our Cactus Hybrid technique. If above your threshold, act, below it, escalate to the cloud or bigger model. Combining Needle 2 with a private DeepSeek-v4-Flash deployment works particularly well for enterprise-level tasks at barely any cost, we can help with this setup. We have put a lot of thoughts into Needle 2 but might still be missing quite a lot, please use the playground in the provided link to test Needle and share your thoughts, always appreciated!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 17d ago · company-app.joinastute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com