# Cactus Needle 3: tiny on-device tool-calling models

> Cactus Compute's 8–29MB models aim to run automation and tool-calling entirely on-device, rivaling far larger cloud systems.

Published by The Open Weights on Sep 16, 2026. Canonical: https://theopenweights.com/news/cactus-needle-3-n6y8

## Key facts

- Company: Cactus Compute
- Model: Cactus Needle 3
- Version: 3
- Category: Text / LLM
- Modalities: Text / LLM, Code
- License: Apache 2.0 (Open weights, commercial use allowed)
- Context window: 8K tokens
- Architecture: NeedleForToolCalling
- Significance: notable
- Published: 2026-09-16
- Last verified: 2026-09-30
- Hugging Face: https://huggingface.co/Cactus-Compute/needle3
- Canonical URL: https://theopenweights.com/news/cactus-needle-3-n6y8

Cactus Compute has released Needle 3, a family of extremely small language models built for on-device tool calling and automation. According to the [model repository](https://huggingface.co/Cactus-Compute/needle3), the models range from just 8MB to 29MB — small enough to ship inside an app rather than call out to a server.

The pitch is that these models can handle the structured, function-calling work that powers automation flows: interpreting a request, choosing a tool, and formatting the call. Cactus claims Needle 3 can match DeepSeek V4 Flash on automation tasks, a notable assertion for models this size, though independent benchmarks aren't yet part of the record.

## Why it matters

Most tool-calling today runs in the cloud, which adds latency, cost, and privacy tradeoffs. A model measured in megabytes changes the calculus:

- It can run locally on phones and edge hardware with no network round trip.
- Under-1B parameters keeps memory and battery demands low.
- The Apache 2.0 license lets developers embed and modify it freely.

The headline number to watch is real-world reliability: automation is unforgiving of malformed tool calls, and sub-30MB models leave little room for error. If Cactus's claims hold up under scrutiny, Needle 3 points toward a future where routine agentic tasks happen entirely on the device in your hand.

## Get the model

- [Hugging Face](https://huggingface.co/Cactus-Compute/needle3)

## Sources

- [Cactus-Compute/needle3](https://huggingface.co/Cactus-Compute/needle3) — Hugging Face, Sep 16, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Cactus Needle 3: tiny on-device tool-calling models", The Open Weights, Sep 16, 2026, https://theopenweights.com/news/cactus-needle-3-n6y8