What can I use LFM3-Omni-2B for?

Give it a spoken question together with a photo, and you get an answer about the picture in text or speech. Give it a .wav recording with the instruction to perform speech recognition in English, and you get a written transcript of what was said. Send it a short video with its soundtrack and a question, and it answers using both what it sees and what it hears.

Can I run LFM3-Omni-2B on my computer?

It runs on your own hardware with a model runtime. The model card mentions Transformers, SGLang, GGUF; check its setup and hardware notes.

What do I need to use LFM3-Omni-2B?

Python with the Transformers library, torch and the other listed libraries. BF16 weights target GPU inference; GGUF files run on CPUs and GPUs with llama.cpp. Memory needs are not documented.

LFM3-Omni-2B: Ask about photos, video and speech by voice (2.17B)

Model details

Original model LiquidAI/LFM3-Omni-2B

Capability unclear

Input Unknown Output Unknown

Follow the model card setup

Ways to use it Run locally

What it does

LFM3-Omni-2B is Liquid AI's first omni-modal model in its LFM3 family, meaning one model that understands text, images, video and audio and answers in text, speech or both. It is built for on-device use, replacing separate speech-recognition, vision, language and text-to-speech models. For videos with sound, it sees and hears at once.

How to use it

Load the weights with the Transformers library from the Hugging Face page, using the checkpoint's own custom code, then give it a system prompt such as the transcription instruction plus your audio file. A GGUF version runs with llama.cpp on CPUs and GPUs.

Common use cases

Give it a spoken question together with a photo, and you get an answer about the picture in text or speech.
Give it a .wav recording with the instruction to perform speech recognition in English, and you get a written transcript of what was said.
Send it a short video with its soundtrack and a question, and it answers using both what it sees and what it hears.

Can I use this?

Needs a model runtime on your computer

Requirements It runs on your own computer or edge device; install Transformers, torch and the other listed Python libraries, then load the model with its custom code enabled.

Caveat By default it picks the output type from the system prompt and input; add an instruction such as respond in text, or respond in interleaved text and audio, to choose.

Worth knowing Licensed under the LFM Open License v1.0. It is a non-reasoning model, so thinking mode is not supported.

Why it's here

Not trending this week

Last seen on the Hugging Face trending list on 4 November 2026. It stays on BuildTube so you can still find it.

412 people have liked it on Hugging Face.
It was downloaded 16,547 times in the last 30 days.

Numbers checked on 8 November 2026; not refreshed since.

Behind it

View model page

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?

Quick questions

What is LFM3-Omni-2B?: LFM3-Omni-2B is Liquid AI's first omni-modal model in its LFM3 family, meaning one model that understands text, images, video and audio and answers in text, speech or both.
What can I use LFM3-Omni-2B for?: Give it a spoken question together with a photo, and you get an answer about the picture in text or speech. Give it a .wav recording with the instruction to perform speech recognition in English, and you get a written transcript of what was said. Send it a short video with its soundtrack and a question, and it answers using both what it sees and what it hears.
Can I run LFM3-Omni-2B on my computer?: It runs on your own hardware with a model runtime. The model card mentions Transformers, SGLang, GGUF; check its setup and hardware notes.
What do I need to use LFM3-Omni-2B?: Python with the Transformers library, torch and the other listed libraries. BF16 weights target GPU inference; GGUF files run on CPUs and GPUs with llama.cpp. Memory needs are not documented.
What license does LFM3-Omni-2B use?: Licensed under the LFM Open License v1.0.

More from this week

P-H3-Image-Comfy Make and edit 8-megapixel images in ComfyUI
Turn short text requests into 8-megapixel images and edit pictures on your own graphics card.
Added 7 Nov
Idol Turn one picture of an object into a 3D Gaussian splat
Idol turns one photo, render or generated image of an object into a 3D Gaussian splat file.
Runs in a terminalAdded 2 Nov
agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
+13,858 stars this weekAdded 3 Nov

Related projects

LFM3-Audio-2B Transcribe, speak and chat by voice (2B)
Same topic: transformers
Needs a model setupAdded 3 Nov
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B Transcribe hour-long recordings (34B)
Same topic: transformers
Needs a model setupAdded 30 Oct
Mistral-Large-4-1T-A52B Chat, code and ask about images (1T, 52B active)
Same topic: transformers
Needs a model setupAdded 31 Oct
LFM3-1.7B Run local chat and tool-calling agents (1.73B)
Same topic: transformers
Needs a model setupAdded 28 Oct
drama-3 Generate multi-speaker audio (35B, 3B active)
Same topic: safetensors
Needs a model setupAdded 21 Oct
indra-ocr Read scanned pages (1.25M recognizer)
Same topic: safetensors
Runs in a terminalAdded 21 Oct

Explore by topic

Post this

For makers

Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.

README badge (Markdown)

[![Featured on BuildTube](https://buildtube.app/badge/hf-liquidai-lfm3-omni-2b.svg)](https://buildtube.app/p/hf-liquidai-lfm3-omni-2b/)

Embed card (HTML)

<iframe src="https://buildtube.app/embed/hf-liquidai-lfm3-omni-2b/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="LFM3-Omni-2B on BuildTube"></iframe>