Pocket-book language learning game runs LFM3-Omni locally via WebGPU
helloiamleonie · x · 2026-11-14
Xenova demoed a cute Duolingo-style language learning game running LFM3-Omni from Liquid AI entirely in-browser via custom WebGPU kernels: one model handles speech recognition, image understanding, conversation, and TTS — fully offline. The author questions why apps like Duolingo don't invest more in on-device AI, which would give users free "premium" features and cut infra costs.
More from Multimodal
- MiniMax H3 Image editing tested at 60MP: concept art to realistic photo in ~2 min on RTX 4090 — daroamer · 2026-11-14
- AI-generated 4D Gaussian Splatting brings Scooby-Doo's Velma to life — buchachos · 2026-11-14
- Encoder-free multimodal LLMs re-learn encoder-like traits in early layers — rdesh26 · 2026-11-14
- Hobbyist uses Grok Ultra and Google models to let AI design its own cyborg arm — Promptmethus · 2026-11-14
- Midjourney now lets you blend up to 20 style-reference images, and anime mixes look striking — Kyrannio · 2026-11-14
- 200+ models trained from scratch: only one multimodal encoding choice matters — sainingxie · 2026-11-14