Cactus-Compute/needle3
text-generation model by Cactus-Compute
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A foundation model for mobiles, wearables, robots, smart home, automotive and microcontrollers. The whole model is a single 8-29 MB file, and we trade general chat capacity to beat models 10x its size on mobile tool calls and match 2-3x bigger models on extraction. Needle does three jobs, all of them on the device: The same engine also runs Whistle, our 16.9 MB speech-to-text model in seven languages. Load whistle.cact beside needle3.cact and the one binary transcribes a clip on its own, or answers it against your tools in a single call and returns the calls and the transcript in one JSON object. Needle 3 is a Laddered Simple Attention Network, our small-model recipe: a Monarch Hadamard MLP in place of the FFN, GQA attention with causal conv taps, engram n-gram memory read by gather, and multi-lane hyper-connections, trained so that every depth from 2 to 20 layers is a…
Read the full model card ↗ · Preview checked 2026-11-03T01:03:26.245Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Cactus-Compute/needle3 is a text-generation model repository published by Cactus-Compute on Hugging Face. The source reports the cactus-needle library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- cactus-needle
- Recent downloads (30 days)
- 125,666
- Cumulative likes
- 323
- Hugging Face trending score
- 49
- Reported safetensors parameters
- Not reported
- Architecture
- NeedleForToolCalling
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-16T06:41:36.000Z
- Last modified
- 2026-10-05T18:01:40.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-10T06:39:59.353Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.