Liquid AI releases LFM3 series of multimodal models
Current overview (not historical)
Liquid AI has released the LFM3 series, a set of multimodal models built on a shared backbone that integrates text, vision, audio, and general modalities. The series includes four 2-billion-parameter models: LFM3-1.7B, LFM3-VL-2B, LFM3-Audio-2B, and LFM3-Omni-2B. The text-focused LFM3-1.7B is approximately 1 GB at 4-bit precision and supports a 256K context window. Newly developed visual and audio encoders are included to accelerate processing. The release emphasizes specialized multimodal capabilities built upon the LFM3-1.7B backbone, marking Liquid AI's expansion into integrated audio-visual processing.
Written with AI from the reporting · updated 10/27/2026
EventGraph Explorer
One time cutoff for reports, relations and evidence.
New at this step ·Liquid AI releases LFM3 family of specialized multimodal models built on shared 2B parameter backbone
- Reports in replay
- 1
- First-party
- 1
- Sources
- 1
Reports first seen at this step · 1
- Hugging Face Blog · First-partyLiquid AI releases LFM3 family of specialized multimodal models built on shared 2B parameter backboneOriginal source ↗
Discovery-time replay; the linked graph and evidence share this cutoff. The full overview and activity remain current.
Event developments
1 developments10/28/2026, 1:46:23 AM
Liquid AI releases LFM3 family of specialized multimodal models built on shared 2B parameter backboneHugging Face Blog
Filtered by first discovery; only representative reports already discovered by this cutoff are shown. Story grouping may have changed later, so this is not a complete historical snapshot.
Relations at this time
Loading time-scoped relations…
Bounded reconstruction, not an exact snapshot: entity names, relationship text and story grouping may include later revisions. Overview and full source archive below remain current.
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Oct 28, 00:00recorded Oct 28, 01:46single sourcerevised
发布 LFM3 系列多模态模型
Read original source ↗ Hugging Face BlogReplay this moment in the explorer
Uncertainty marks flag where to check the sources; they are not proven causation.
Full source archive (current)
Current public reports; outside the historical replay.
First-party sources · 1 reports
- Hugging Face Blog · Oct 28, 01:16Liquid AI releases LFM3 family of specialized multimodal models built on shared 2B parameter backbone
Liquid AI introduces LFM3, a new generation of Liquid Foundation Models ranging from 1.7B to 2B parameters that unify text, vision, audio, omni, and decision models on a single shared backbone. Key improvements include a tri-hybrid architecture combining short convolutions and attention, enabling LFM3-1.7B to outperform the larger LFM2.5-2.6B with 35% fewer parameters. The text model fits within approximately 1 GB at 4-bit precision and supports a 256K context window for on-device agent deployment. Four specialized model variants -- text, vision, audio, and omni -- are derived from the base model and can be fine-tuned on a single GPU. LFM3-1.7B-Base was pre-trained on 22 trillion tokens, with the final 3.5 trillion tokens focused on agentic traces and tool calls to extend the context window.
Read original source ↗
Independent coverage · 0 reports
No verifiable reports in this group yet.
Different reports do not necessarily disagree. Check original sources and publication dates.
Report timeline
Explore every side through dated source reports.
- Hugging Face BlogSelectedLiquid AI releases LFM3 family of specialized multimodal models built on shared 2B parameter backbone
Liquid AI introduces LFM3, a new generation of Liquid Foundation Models ranging from 1.7B to 2B parameters that unify text, vision, audio, omni, and decision models on a single shared backbone. Key improvements include a tri-hybrid architecture combining short convolutions and attention, enabling LFM3-1.7B to outperform the larger LFM2.5-2.6B with 35% fewer parameters. The text model fits within approximately 1 GB at 4-bit precision and supports a 256K context window for on-device agent deployment. Four specialized model variants -- text, vision, audio, and omni -- are derived from the base model and can be fine-tuned on a single GPU. LFM3-1.7B-Base was pre-trained on 22 trillion tokens, with the final 3.5 trillion tokens focused on agentic traces and tool calls to extend the context window.
Event activity trend
- Latest comparable
- 3
- Comparable peak
- 1010月28日 02:00
- 24h change
- -50%
The chart compares consistently observed participants only. Hover or tap to inspect each hour; use arrow keys to move between observations.