SSyncDev

LFM3-Omni-2B

SyncDev model directory · Profile updated Nov 17, 2026

Compare with another model

LFM3-Omni-2B is Liquid AI's open any-to-any model: image, video, audio and text in; text and speech out, with multimodal tool calls on-device.

Key specifications

Specification score
34.9
License
LFM Open License v1.0

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Open weights under LFM Open License v1.0; no hosted price confirmed.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input
  • Image input
  • Audio input
  • Video input

Produces

  • Text output
  • Audio output

Capabilities

Function callingVisionAudioOpen weights

What is LFM3-Omni-2B?

Point a camera at a machine, ask out loud what the warning light means, and hear the answer. LFM3-Omni-2B is built for exactly that kind of interaction on low-power hardware: a 2.17B-parameter model that takes images, video (with or without its soundtrack), 16 kHz audio and text, and replies in text, 24 kHz speech, or both interleaved.

Liquid AI released it on 27 October 2026 as the most general member of the LFM3 family.

No thinking, by design

This is a non-reasoning model. enable_thinking=True is not supported. That keeps replies fast, which suits spoken interaction, but it also means harder visual reasoning falls to other models. Liquid's own LFM3-VL-2B reasons and scores better on vision-only work.

Components and limits

Item Detail
Weights LiquidAI/LFM3-Omni-2B
Parameters 2.17B
Encoders LFM3 vision encoder; causal audio encoder; LiquidCodec tokenizer
Context 32K tokens, input + output
Images Native resolution, up to 2,048 tokens each
Video 2 fps, 4 to 384 frames by default
Output modes text, audio, interleaved via generation_mode
Languages 16 for text; 19 speech locale entries
Licence LFM Open License v1.0

For speech output, Liquid suggests audio_temperature=0.4 and audio_repetition_penalty=1.2. Text output works fine greedy.

What it does well, and what it does not

Liquid reports Daily-Omni 70.1, the top score in its table and ahead of Qwen2.5-Omni-3B's 58.8, and RealWorldQA 64.7. DocVQA comes in at 92.5.

The weaker rows are just as instructive. OmniBench (46.3) trails Qwen2.5-Omni 7B. VoiceBench (64.7) trails Gemma 4 E4B (72.9), and internal tool calling (52.2) does too. English ASR WER of 6.4 is behind Phi-4-multimodal. In short: a strong generalist for audio-visual questions, not the best at any single channel.

Tool calls across modalities

Pass functions via tools= in apply_chat_template(). The model emits <tool_call> blocks; your app parses and executes them and returns results as tool messages. The useful part is that the request can be spoken and the context visual, so "order another one of these" with a photo becomes a function call.

Runtime quirks

  • SGLang serves text output only.
  • llama.cpp includes a realtime speech server, but ignores --video-fps; video is fixed at 2 fps there.
  • Transformers needs 5.20.2+ with trust_remote_code=True.

Evaluating an omni model

Test each channel alone first, then together. Measure ASR on your audio, VQA on your images, and speech quality by ear. Then run combined tasks: a spoken question about a short clip. If the combined task is no better than chaining specialist models, chain the specialists. If it is close and simpler to run, the single checkpoint wins.

A much larger open alternative is Nemotron 3 Nano Omni 30B A3B Reasoning. Liquid's d1-Omni-2B decision model is built on this one. More under any-to-any and on Liquid's provider page.

How to evaluate LFM3-Omni-2B

Compare the model on the work you need to complete.

Tasks and inputs

LFM3-Omni-2B is listed for Any-to-any, Audio-text-to-text, Multimodal. It accepts text, image, audio, video and produces text, audio. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Compare pronunciation, voice consistency and time to the first playable audio. Check the service’s billing unit for the actual script.

Choosing a deployment

The weights are downloadable under LFM Open License v1.0. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

Images, video with or without audio, 16 kHz audio and text in; text, 24 kHz speech or interleaved text and speech out.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

google

google/gemma-4-E2B-it

google/gemma-4-E2B-it is a source-linked Hugging Face repository assigned to Any-to-any. Its recorded task interface accepts text, image, audio, video and produces text, image, audio, video.

131.07K context

google

google/gemma-4-E4B-it

google/gemma-4-E4B-it is a source-linked Hugging Face repository assigned to Any-to-any. Its recorded task interface accepts text, image, audio, video and produces text, image, audio, video.

131.07K context

lmstudio-community

lmstudio-community/gemma-4-E4B-it-MLX-4bit

lmstudio-community/gemma-4-E4B-it-MLX-4bit is a source-linked Hugging Face repository assigned to Any-to-any. Its recorded task interface accepts text, image, audio, video and produces text, image, audio, video.

32.77K context

Qwen

Qwen/Qwen3-Omni-30B-A3B-Thinking

Qwen/Qwen3-Omni-30B-A3B-Thinking is a source-linked Hugging Face repository assigned to Any-to-any. Its recorded task interface accepts text, image, audio, video and produces text, image, audio, video.

— context

Qwen

Qwen/Qwen2.5-Omni-7B

Qwen/Qwen2.5-Omni-7B is a source-linked Hugging Face repository assigned to Any-to-any. Its recorded task interface accepts text, image, audio, video and produces text, image, audio, video.

32.77K context

Anthropic

Claude Sonnet 3.5 v2

Balanced Claude model for coding, analysis, agent workflows, and cost control

200K context