A device-by-device cheat sheet for running free local AI models offline
alex_verem · x · 2026-11-19
alexverem shares a cheat sheet matching devices to free local models, all downloadable from Hugging Face and runnable with Wi-Fi off: phone → Gemma 4 E2B, 8GB laptop → Gemma 4 E4B, 16GB laptop → Qwen3.5 9B, 32GB MacBook → Qwen3.8 27B, 32GB-VRAM gaming PC → Nemotron 3.5 Bolt 74B, company server → DeepSeek V4.1 Flash. Posted partly to promote his newsletter.
Related event: Cheat Sheet: Free Local Models for Every Device(2 posts)→
More from Infra
- OpenAI models find up to 14% PPA gains on AMD GPU IP, improve custom Jalapeño chip — OpenAI · 2026-11-19
- A Local Model for Every Device: 6 Free Offline Models from Phones to Servers — alex_verem · 2026-11-19
- NVIDIA driver 621.24 constantly writes to SSDs via NVDisplay.Container logging — giveen · 2026-11-19
- NVIDIA Ships VSS 3.3 and Cosmos to Accelerate Visual AI Agents on Jetson — NVIDIAAI · 2026-11-19
- Intel Foundry bull case: TSMC's capacity crunch opens second-source opportunity — BenBajarin · 2026-11-19
- Firecrawl Local Goes Open Source: 37x Faster Rust Scraping, 11MB Idle Memory — gaganghotra_ · 2026-11-19