LFM 3 1.7B runs on-device on folding iPhone at a stable 60+ tokens/s via MLX
helloiamleonie · x · 2026-11-05
Developer @adrgrondin demos the new LFM 3 1.7B model running fully on-device on a folding iPhone ("Duo"), using the latest MLX and the updated Locally for Duo app. It works folded or unfolded and sustains 60+ tokens/s, a solid showcase of small-model local deployment on phones.
Related event: Liquid AI Releases LFM 3 Small Models That Run Locally on iPhone Duo(2 posts)→
More from Infra
- Nationwide voters rejected data centers in 40+ provisions as AI's scientific wins go unnoticed, argues investor — beffjezos · 2026-11-05
- CMU paper unifies pretraining, SFT and RL into one likelihood-based algorithm — burny_tech · 2026-11-05
- Thousands of GPUs sit idle while frontier labs scramble for compute — _arohan_ · 2026-11-05
- Ontario's Ford Government to Approve AI Data Centres 'Sooner Rather Than Later' — shadowt1tan · 2026-11-05
- PyTorch Day Japan agenda: backpropagation for real-time robot inference with ExecuTorch — PyTorch · 2026-11-05
- VibeSys uses agents to auto-generate Qwen3.8 serving engines for AWS Trainium2 — bariskasikci · 2026-11-05