{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-10-27-liquid-ai-lfm3-family/","md":"https://postcutoff.com/e/2026-10-27-liquid-ai-lfm3-family/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-27-liquid-ai-lfm3-family","date":"2026-10-27","date_precision":"day","short_title":"Liquid AI releases LFM3","deck":"Six open 2B-class models (text, vision with video, audio, its first omni model, two decision models) on one 1.7B backbone","takeaway":null,"category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Liquid AI on Hugging Face: Build specialized multimodal models with LFM3 (Oct 27)","url":"https://huggingface.co/blog/LiquidAI/lfm3","type":"official","group":"primary","domain":"huggingface.co"},{"n":2,"title":"Hugging Face: LiquidAI/LFM3-1.7B","url":"https://huggingface.co/LiquidAI/LFM3-1.7B","type":"code","group":"primary","domain":"huggingface.co"}],"official":2,"filed":"2026-10-29","updated":"2026-10-29","orgs":["Liquid AI"],"title":"Liquid AI releases LFM3: six open 2B-class models (text, vision with video, audio, its first omni model, two decision models) on one 1.7B backbone","summary":"On Oct 27, 2026 Liquid AI released LFM3, its third generation of Liquid Foundation Models: LFM3-1.7B (text, 256K context, ~1 GB at 4-bit), LFM3-VL-2B (first LFM with video input), LFM3-Audio-2B, LFM3-Omni-2B (its first omni model, text/vision/audio in, text and speech out) and the d1-2B and d1-Omni-2B decision models, all branched from one 1.7B base and open-weight under the LFM Open License. Liquid reports the 1.7B text model beats its 2.6B predecessor with 35% fewer parameters, scoring 38.42 vs 3.02 on WebArena-Verified.","key_facts":["Architecture: tri-hybrid mix of 13 gated short convolutions (kernel 7), 5 sliding-window attention layers (256-token window) and 6 global attention layers, with head-wise gated attention and partial RoPE; chosen by hardware-in-the-loop search over 14 device/backend combinations (phones, Raspberry Pi 5, laptops, CPUs, GPUs, Qualcomm Hexagon NPU)","Training: LFM3-1.7B-Base pre-trained on 22T tokens; the last 3.5T tokens are mid-training with more agentic traces and tool calls, extending context to 256K","Vendor numbers: LFM3-VL-2B (1.9B) raises the average over 62 vision benchmarks to 71.4 from 57.6 for LFM2.5-VL-3B, 'on par with Gemma 4 12B'; new 164M vision encoder uses 2.2x fewer FLOPs than Qwen3.5-2B's; audio time-to-first-token as low as 50 ms; LiquidCodec decodes speech ~87x real time on one Apple M4 Max CPU thread; d1-2B scores 75.5 vs 64.0 for d1-3B on ImajevBench","Robotics: Liquid adapted LFM3-VL-2B into orchestration, navigation and manipulation models for a robot arm and mobile navigation (demo video)","Licence: LFM Open License v1.0; Hugging Face lists LFM3-1.7B since Oct 23 (published Oct 27 with the blog), ~16k downloads and 436 likes by Oct 29"],"key_numbers":[],"tags":["small-models","on-device","open-weights","multimodal","omni","edge","agents"],"science":null,"body_md":"## What happened\n\nLiquid AI moved its whole small-model line to one new backbone and shipped text, vision, audio, omni and decision variants at once,\neach small enough to fine-tune on one GPU and run on a phone or laptop.\n\n## Why it matters\n\nMost frontier progress is in huge models; LFM3 is aimed at the opposite end, where agents run on-device. The benchmark gains are the\nvendor's own and await independent tests.","disputed":[],"related":[{"id":"2026-10-13-liquid-ai-lfm2-5-24b-a2b","url":"https://postcutoff.com/e/2026-10-13-liquid-ai-lfm2-5-24b-a2b/","date":"2026-10-13","date_precision":"day","short_title":"Liquid AI releases LFM2.5-24B-A2B, an open-weight 24B/2B-active MoE built for on-device agents","deck":null,"takeaway":"Small active-parameter MoEs are becoming the default design for agents that run on laptops.","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":3,"official":2,"filed":"2026-10-15","updated":"2026-10-15","orgs":["Liquid AI"]},{"id":"2026-10-05-liquid-ai-d1-decision-models","url":"https://postcutoff.com/e/2026-10-05-liquid-ai-d1-decision-models/","date":"2026-10-05","date_precision":"day","short_title":"Liquid AI joins the decision-model wave","deck":"D1 API ($0.04/M input) and open-weight d1-3B and d1-omni-600M for edge devices","takeaway":"In two weeks most of the AI industry shipped \"decision models\": TypeSafe's Jev, then Cloudflare's Clef, Perplexity's Decider, Liquid AI's d1, OpenAI's Decisions API and Microsoft's Decision-1.","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":3,"filed":"2026-10-10","updated":"2026-10-10","orgs":["Liquid AI"]}],"people":[],"posts":[],"videos":[],"models":[{"id":"liquid-lfm3-1-7b","name":"LFM3-1.7B","url":"https://postcutoff.com/m/liquid-lfm3-1-7b/"}],"changes":[{"date":"2026-10-29","type":"filed","text":"Created (Hugging Face blog and model API read directly) (news agent)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-29","run":null,"sources_read":"Hugging Face blog and model API read directly) (news agent","updated":"2026-10-29","human_review":null,"version":{"date":"2026-10-29"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":180,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":119,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":210,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":149,"in_training_data":false}],"short_url":null}