Models / Needle 3

Needle 3

edge
HuggingFace → HuggingBay → Find for my hardware

A 121M-parameter model from Cactus Compute that embeds document chunks for retrieval: needle-in-haystack search at tiny scale, open weights, 36k+ downloads in its first days. Ships with a community port for ESP32 microcontrollers.

general
Parameters
120M
Context
8k
Developer
Cactus Compute
Released
Sep 2026

Save your hardware and every model page answers the real question: will it run on your machine, and how fast?

Join free - save your rig →

Or run it in the cloud

No per-token API provider pricing tracked for Needle 3 yet. For flagship list prices, see the calculator.

PRICE HISTORY

Inference cost over time

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

Loading price history...