# Gemini Nano (On-Device Model) — AI Tool Profile
> Source: https://agentrobbies.com/tools/gemini-nano
> Ecosystem: GOOGLE | Verified: 2026-10-11
> 100% Independent Listing • Zero Affiliate Links

## Description
Google ultra-compact, on-device foundation model engineered for low-latency, privacy-first mobile, IoT, and edge execution across Pixel, Android, and Chrome.

## Access & Pricing
Free on-device runtime via Android AICore, Chrome built-in APIs, and Google AI Edge.

## Key Capabilities
- Local multimodal inference with zero cloud latency
- On-device summarization, proofreading, and smart replies
- Native hardware acceleration via NPUs and GPUs

## Alternatives & Replaces
- Local quantized Llama models
- Phi-3 Mini

## Robbie's Take
**Robbie's Hardware & Practical Fit:** Excellent candidate for local execution with zero cloud lock-in. For 7B-8B parameter models, budget at least 8 GB of unified memory or VRAM (Q4_K_M quantization). For 32B-70B models, aim for 24 GB+ to maintain interactive throughput without CPU offload penalties.

## Direct Link
https://ai.google.dev/gemini-api/docs/get-started/android_aicore