Skip to main content
Nishchay Kaushik// lead engineer
  • Experience
  • Blog
  • Projects
  • Contact
/
    Searching articles...
    ∅

    No posts found

    No articles matched ""

    Browse all writing →
    ↑↓ navigate↵ selectesc close
    All articles →
      Searching articles...
      ∅

      No posts found

      No articles matched ""

      Browse all writing →
      ↑↓ navigate↵ selectesc close
      All articles →
      • Experience→
      • Blog→
      • Projects→
      • Contact→
      Home/Writing/Tags/#Gemma
      3 Articles

      Articles tagged #Gemma

      Curated technical writing and architecture reflections categorized under #Gemma.

      Running Gemma 4 Locally on iOS and Android: The Google AI Edge Gallery Guide
      Series: AiMay 24, 2026
      11 min read

      Running Gemma 4 Locally on iOS and Android: The Google AI Edge Gallery Guide

      Step-by-step guide to run Gemma 4 locally on iPhone or Android via Google AI Edge Gallery. Learn how Multi-Token Prediction unlocks fast on-device agents.

      How to Install and Run Ollama in Termux on Android (2026 Guide)
      Series: AiMay 23, 2026
      5 min read

      How to Install and Run Ollama in Termux on Android (2026 Guide)

      Step-by-step guide to run Ollama in Termux on Android. Run lightweight Qwen 2.5, Gemma & Llama models with one-line install, WebUI, and no root.

      How to Run LLM Models on Old Android Devices Locally
      Series: AiFeb 13, 2026
      4 min read

      How to Run LLM Models on Old Android Devices Locally

      Turn an old 2GB–4GB Android phone into an offline AI server using llama.cpp in Termux. Fix memory errors, optimize CPU threads, and prevent overheating.

      Explore Other Topics:
      #AI#Adblock#Adguard#Adguardhome#Ads#Ai-agents#Android#Anythingllm#Appsec#Artificial-intelligence#Astro#Astros#Automation#Beginner-homelab-guide#Beginners#Beszel#Blog#Bmad#Browsers#Claude-code#Cloudflare#Cloudflare-tunnels#Crowdsec#Debian#Developer-experience#Devops#Docker#Docker-compose#Documentation#Dozzle#Edge-ai#Frontend#Gemini-flash#Gemma#Gemma-4#Gemma4#Generative-ai#Gin#Git#Github#Github-spec-kit#Golang#Google#Google-ai-edge-gallery#Google-edge#Google-meet#Google-photos#Guide#Guide2026#Hello-world#Home#Home-lab#Immich#Ios#Javascript#Jellyfin#Linux#Llama-cpp#Llama-server#Llamacpp#Llm#Lmmich#Local-ai#Local-ai-models#Local-llm#Mac#Machine-learning#Mcp#Mini-pc#Mobile-ai#Monitoring#Nextjs#Ntfy#Oidc#Old-android#Ollama#On-device-ai#Open-source#Opengraph#Opensource#Openspec#Outline#Parental-control#Performance#Personal-ai#Phishing#Pocketpal#Privacy#Programmatic-video#Programming-blogs#Prompt-engineering#Qwen#Rclone#React#Remotion#Rust#Satori#Security#Self-hosted#Self-hosting#Selfhosted#Selfhosting#Sharp#Software-development#Software-engineering#Spec-driven-development#Streaming#Superpowers#Sysadmin#Tailscale#Takumi#Termux#Traefik#Tutorial#Vercel#Vibe-coding#Video#Video-engineering#Waf#Webdev#Webrtc#Wiki#Windows#Zoom#Architecture#Engineering#Homelab#TypeScript

      Featured

      • AdGuard Home: Stop Ads & Trackers for Your Entire Family
      • Top 4 ways to Run LLM locally on Android and iOS
      • Replace Google Photos: Self‑Host Immich in 2026

      Socials

      • GitHub↗
      • LinkedIn↗
      • Twitter / X↗

      Site Links

      • RSS
      • Sitemap
      • Privacy Policy

      © 2026 Nishchay Kaushik

      ↑ Back to top