Needle 3

Cactus Compute

A 121M-parameter open model for tool calling, structured extraction and text embedding on tiny devices. One set of weights ships as an intelligence ladder: every depth from 2 to 20 layers is a deployable model, an 8-29 MB CQ2-bit binary.

Specs

Model

Family
Needle
Variant
3
Parameters
121M
Weights
Open
License
Apache-2.0

Limits

Context
8,192 tokens

Modalities

Input
Text
Output
Text

Capabilities

Tool calling
Yes

Dates

Released
16 Sept 2026

More from Cactus Compute

All models

Needle 2

Cactus Compute

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.

Apache-2.05w ago

Keep up with the tools

An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.