Cactus-Compute/needle3 — new model trending #30 on Hugging Face
Cactus Compute released Needle 3, a 121M-parameter model shipped as an 8–29 MB file for on-device tool calls, extraction, and embeddings.
Needle 3 is a foundation model from Cactus Compute targeting mobiles, wearables, robots, automotive, and microcontrollers, delivered as a single 8–29 MB file. Built on a Laddered Simple Attention Network with a Monarch Hadamard MLP, engram n-gram memory, and CQ2-bit quantization, the 121M-parameter model performs tool calling, grammar-constrained structured extraction, and text embedding entirely on-device. Cactus claims it beats models 10x its size on mobile tool calls, and LoRA fine-tuning on DroidCall lifts subnetworks 18–36 points, with tuned 4-layer (29M-parameter) subnetworks passing DeepSeek V4 Flash.
- Single 8–29 MB file runs tool calls, extraction, and embeddings on-device
- Every depth from 2 to 20 layers is a deployable subnetwork
- Grammar-constrained decoding guarantees structured output parses
- Fine-tuned subnetworks from 29M parameters reportedly pass DeepSeek V4 Flash
From the original article
4 min read at huggingface.cotext-generation · 46,399 downloads · 157 likes · license apache-2. 0
By Cactus-Compute · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.