aiqbenchInformații despre AI & calcul cuantic

...

localeBeta.label localeBeta.notice localeBeta.readInEnglish

perspectiva aiqbenchProduse AI

This release marks a significant step in edge AI by demonstrating that specialized tool-calling tasks can be executed on constrained hardware like Raspberry Pis and smartphones without GPUs or NPUs. The model's efficiency, achieved through quantization to CQ2-bit and a custom Simple Attention Network architecture, enables fully offline sessions within 28MB of RAM for specific device control and data extraction workflows.

Sursă care acoperăMarkTechPost

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM

MarkTechPost14 august 20264 min de cititArticolul și perspectiva sunt în engleză.

Cactus Compute released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The full model is a single 14MB binary that runs a session in about 28MB of RAM. It leads both Seal-Tools splits while targeting hardware with no GPU and no NPU. The post Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM appeared first on MarkTechPost.

Cactus Compute has released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The entire model ships as a single 14MB binary that runs a full session in about 28MB of RAM. Weights are trained and deployed at CQ2-bit using Cactus Quants, and the model is sealed inside the company’s own C++ engine, so there is no runtime to install and no download at inference time. Reported decode throughput is 500 tokens/sec on a Raspberry Pi…

Extras afișat conform termenilor RSS ai publicației · 81 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe MarkTechPost ↗Întreabă despre acest articol