[360Labs.ai]
[360Labs.ai]
{ 360Labs }Model
{ slm360-lensnano }· Released

SLM360 LensNano

869KB of AI That Replaces Your Cloud

// overview

A complete on-device voice + vision AI engine designed for smart glasses. Handles NLU, voice command classification, entity extraction, and OCR. 1.67M parameters in 869KB, sub-10ms inference on CPU, 100% offline. Built on the 360 Engine in pure Rust with zero garbage collection.

// specs

Specifications

1.67M

Parameters

869KB

Model Size (INT4)

<10ms

Latency

192

Embedding Dim

4

Layers

6

GQA Heads

2K

Vocabulary (BPE)

55MB

Pipeline Footprint

100%

Accuracy

15

Voice Intents

99

Languages (STT)

$0

Cost per Query

// architecture

Architecture

 1  Stage 1 (Always On, 17MB, ~5mW): Microphone > 360 VAD (2MB) > 360 Wake (15MB)
 2  Stage 2 (On Demand, 43MB): 360 STT (42MB) > SLM360 NLU (869KB) > Action
 3  NLU: 192-dim, 4 layers, 6 GQA heads, SwiGLU + RoPE + RMSNorm
 4  Vision: 360 OCR for reading signs, menus, prescriptions, labels
 5  Framework: 360 Engine (Rust, zero GC), GPU training via 360 Tensor (Metal/CUDA)
// features

Features

  • 0115 voice intents: navigate, call, message, capture, music, fitness, weather, alarms, shopping, translate, notifications, focus mode, identify, read text, assistant
  • 02Entity extraction for contacts, locations, times, durations, languages, frame types
  • 03360 OCR Vision: on-device neural OCR for real-world text recognition
  • 04Hindi + English with native Hinglish code-mixing support
  • 0599 languages supported via STT engine
  • 06100% on-device. Zero data leaves the glasses. Works offline and in airplane mode
  • 07OEM-ready with configurable wake word per brand
  • 08Rust SDK, ARM-native, ONNX export for ARM, x86, WASM, RISC-V
// deployment

Deployment

  • 01ARM-native for smart glasses hardware
  • 02ONNX export for ARM, x86, WASM, RISC-V
  • 03OEM SDK integration with configurable wake words
Try Now →
// end of modelSLM360 LensNano