Needle
A 26M-param model that routes tool calls on phones and watches
The Panel's Take
Needle is a tiny 26-million-parameter language model built specifically for function calling—the task of deciding which tool to invoke based on a user's natural language request. Developed by Cactus-Compute and released under MIT, it was pretrained on 200 billion tokens using 16 TPU v6e chips, then post-trained on 2 billion curated function-call examples distilled from Google's Gemini 3.1. The result: a model small enough to run on a phone or smartwatch that can reliably pick the right tool with sub-100ms latency. The architecture is called a "Simple Attention Network" and deliberately strips away generative capabilities, focusing entirely on routing accuracy. You hand Needle a list of available tools and a user query, and it outputs a structured JSON function call—nothing more. This keeps the binary tiny, the inference fast, and the memory footprint under control on edge hardware. Why does this matter? Today's personal AI assistants require a round-trip to the cloud for every tool dispatch, adding latency and raising privacy concerns. Needle makes it possible to keep that decision-making on-device, calling the cloud only when the tool itself requires it. It's early (258 GitHub stars today, trending hard), but the idea of a dedicated tiny router model is compelling enough that several phone OEMs are reportedly experimenting with it.
Share this verdict
Needle verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/needle-26m-function-calling-on-device-mit-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare Needle with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/needle-26m-function-calling-on-device-mit-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/needle-26m-function-calling-on-device-mit-2026" alt="Needle Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/needle-26m-function-calling-on-device-mit-2026)<iframe src="https://shiporskip.io/embed/needle-26m-function-calling-on-device-mit-2026" title="Needle ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“If you're building any kind of personal agent or on-device assistant, Needle solves the tool-routing problem cleanly. The MIT license and Hugging Face weights make integration straightforward—drop it in, point it at your tool list, done.”
“258 stars and 8 forks isn't exactly a battle-tested library. It's a research preview that hasn't been stress-tested on diverse real-world tool schemas. Wait for benchmarks from third parties before trusting this in production.”
“Dedicated micro-models for specific reasoning subtasks is the architecture path forward. Needle hints at a future where your device runs a dozen tiny specialists rather than one giant generalist—dramatically better for privacy, latency, and battery life.”
“The idea of AI assistants on wearables that actually respond instantly instead of spinning for 3 seconds on every request is genuinely exciting for creative workflows—imagine voice-triggering design tools from your watch without a cloud hop.”