Liquid AI ships LFM3 on-device small model family; 1.9B vision model rivals 12B-class
mhdfaran · x · 2026-10-28
Liquid AI released LFM3, a family of tiny on-device models spanning text, vision, audio, and decision tasks.
- Text model supports 256K context; audio model covers 18 languages; decision models return structured outputs for request classification and routing
- The 1.9B vision model reportedly performs competitively with Gemma 4 12B in Liquid's own evaluations
- Developers can build local assistants that handle documents, understand images/video, and trigger tools via voice commands
- Fine-tuning works on a single GPU; running locally keeps data on-device and cuts dependence on cloud APIs
More from Infra
- EmbeddingGemma 2 runs real-time embeddings on a MacBook CPU alone: 20ms text, 100ms images — generativist · 2026-10-28
- Nebius benchmark: 8 small GPU replicas yield 42.5% more Cosmos video per hour — shashib · 2026-10-28
- Data centers become the new front line as AI, cyber, physical and OT threats converge — ChuckDBrooks · 2026-10-28
- preowned turns macOS built-in Apple models into an OpenAI-compatible local API — pcuenq · 2026-10-28
- 2,100+ tok/s/user for DeepSeek V4.1 Flash on 8× AMD MI355X, 2.8x faster than open-source — JiaZhihao · 2026-10-28
- LFM3-VL-2B Runs Real-Time Video Captioning In-Browser via WebGPU — xenovatech · 2026-10-28