Liquid AI ships LFM3-1.7B, a 1.7B conversational model built for edge deployment
JosephJacks_ · x · 2026-10-28
Liquid AI released LFM3-1.7B on Hugging Face: a 1.7B-parameter conversational text-generation model designed for edge deployment, runnable locally without the cloud. The model card lists 16 supported languages, a 256k context window, custom code, and an lfm1.0 license, with Safetensors weights available. It's the smallest text model in the new LFM3 family, targeting low-cost on-device chat.
Related event: Liquid AI Launches LFM3 Family of Small Multimodal Models(35 posts)→
More from Models
- Gemini Reviews Your Chats by Default — the Only Opt-Out Is Deleting All Your Conversations — Kyrannio · 2026-10-28
- Open model demand debate: enterprise self-hosting is overestimated, demand comes from products — zephyr_z9 · 2026-10-28
- DeepSeek V5 model IDs spotted in official Harness test suite — zyxciss · 2026-10-28
- Google's AI Mode can't even surface Google's own docs, SEO expert Lily Ray complains — lilyraynyc · 2026-10-28
- Altman's 'alignment was easier than expected' claim clashes with Astra hacking findings — GarrisonLovely · 2026-10-28
- Mistral starts serving DeepSeek V4.1 Flash and GLM 5.3 Flash low-cost models — MistralAI · 2026-10-28