PocketPal AI (9.4k GitHub stars) runs open-source LLMs offline on your phone
alex_verem · x · 2026-11-17
alexverem urges running open-source AI locally on your phone: the free PocketPal AI app with a 2-4GB model works offline with no account or subscription, ideal on planes or in dead zones. Install from app stores, download Gemma or Qwen, 10 minutes setup. The MIT-licensed repo has 9.4k GitHub stars.
Related event: PocketPal Brings Open-Source AI Models to Phones Offline(2 posts)→
More from Infra
- Philox RNG-to-tensor assignment is extremely sensitive to hardware details — ezyang · 2026-11-17
- Why tensor parallelism breaks RNG reproducibility in model init — ezyang · 2026-11-17
- Bittensor's Engy tops Venice's AI inference volume despite 28x smaller valuation — markjeffrey · 2026-11-17
- Fractile raises $720M for AI inference chips, betting inference cost breaks AI economics first — YvesMulkers · 2026-11-17
- DeepSeek V4.1 Flash on Vera Rubin NVL72: 63-93x per-chip throughput vs GB300 in vLLM benchmarks — vllm_project · 2026-11-17
- First DeepSeek V4.1 Flash results on Vera Rubin NVL72: up to 93.3x per-chip throughput vs GB300 — vllm_project · 2026-11-17