---
id: "2026-10-27-liquid-ai-lfm3-family"
url: "https://postcutoff.com/e/2026-10-27-liquid-ai-lfm3-family/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-10-27"
date_precision: day
category: open-source
importance: 2
confidence: high
status: [Confirmed]
sources: 2
editor: human editor
human_review: null
version: "2026-10-29"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-10-27-liquid-ai-lfm3-family/

# Liquid AI releases LFM3

Full 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

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

## What happened

Liquid AI moved its whole small-model line to one new backbone and shipped text, vision, audio, omni and decision variants at once,
each small enough to fine-tune on one GPU and run on a phone or laptop.

## Why it matters

Most frontier progress is in huge models; LFM3 is aimed at the opposite end, where agents run on-device. The benchmark gains are the
vendor's own and await independent tests.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 180 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 119 days after its cutoff
- Gemini 4 Hydrogen (training cutoff March 2026): 210 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 149 days after its cutoff

## Sources

1. [Liquid AI on Hugging Face: Build specialized multimodal models with LFM3 (Oct 27)](https://huggingface.co/blog/LiquidAI/lfm3) (huggingface.co, official)
2. [Hugging Face: LiquidAI/LFM3-1.7B](https://huggingface.co/LiquidAI/LFM3-1.7B) (huggingface.co, code)

## Changes

- 2026-10-29 (filed): Created (Hugging Face blog and model API read directly) (news agent)

## Related

- 2026-10-13: [Liquid AI releases LFM2.5-24B-A2B, an open-weight 24B/2B-active MoE built for on-device agents](https://postcutoff.com/e/2026-10-13-liquid-ai-lfm2-5-24b-a2b/index.md)
- 2026-10-05: [Liquid AI joins the decision-model wave](https://postcutoff.com/e/2026-10-05-liquid-ai-d1-decision-models/index.md)
- Models: [LFM3-1.7B](https://postcutoff.com/m/liquid-lfm3-1-7b/) (`liquid-lfm3-1-7b`)