LiquidAI/LFM3-Omni-2B
any-to-any model by LiquidAI
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model. Find more information about the LFM3 family in our release blog post. The LFM3 family includes base, text, vision, audio, omni, and decision models. Property Specification Checkpoint Post-trained omni-modal model Parameters 2.17B total Architecture LFM3 backbone, LFM3 vision encoder, LFM3 causal audio encoder, LiquidCodec audio tokenizer. Inputs Text, images, video with or without its soundtrack, and 16 kHz audio. Images and video are processed at native resolution; each 2×2 block of patches becomes one language token. Video is sampled at 2 fps. Outputs Text, 24 kHz speech, or interleaved text and speech Context length 32K tokens (input + output) Vocabulary 128,000 text tokens…
Read the full model card ↗ · Preview checked 2026-10-28T09:26:56.915Z
Inside the original model card — Document outline
- LFM3-Omni-2B
- Model details
- Inference
- Sampling parameters
- Generation modes (optional)
- Transformers quick start
- Usage examples
- Fine-tuning
- Performance
- Omni
- Vision
- Audio
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
LiquidAI/LFM3-Omni-2B is a any-to-any model repository published by LiquidAI on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- any-to-any
- Library
- transformers
- Recent downloads (30 days)
- 5,695
- Cumulative likes
- 251
- Hugging Face trending score
- 233
- Reported safetensors parameters
- 2,166,928,384
- Architecture
- Lfm3OmniForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-21T16:58:40.000Z
- Last modified
- 2026-10-28T23:16:38.000Z
Compatibility and lineage
Reported languages: en, ar, zh, fr, de, it, ja, ko, pt, es, vi, th, id, hi, ru, pl, da, el, fi, he, nl, sv, tr
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:49:30.141Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.