Data as of October 27, 2026 · How the score is built
LFM3-Omni-2B
Decision readingLFM3-Omni-2B is tracked, but not publicly ranked yet. Published speech or voice results from Liquid AI LFM3 audio and omni evaluation appear below. They do not produce a weighted text-model score.
Released Oct 27, 2026 — see all recent releases
Voice benchmark evidence
Liquid AI LFM3 audio and omni evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not publishedLiquidAI model documentation
- Context window
- 32KLiquidAI model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- LFM Open License v1.0 weights on Hugging Face with GGUF, ONNX and MLX exports, released October 27, 2026 with a 32K context. It takes text, images, video with or without its soundtrack, and 16 kHz audio, and returns text, 24 kHz speech, or both. Thinking mode is not supported.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordLiquidAI model documentation
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track LFM3-Omni-2B, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
LFM3-Omni-2B is a open weight model with a 32K context window. No explicit reasoning mode is documented in this profile.
LFM Open License v1.0 weights on Hugging Face with GGUF, ONNX and MLX exports, released October 27, 2026 with a 32K context. It takes text, images, video with or without its soundtrack, and 16 kHz audio, and returns text, 24 kHz speech, or both. Thinking mode is not supported.
LFM3-Omni-2B is Liquid AI’s first omni model: a 2.17B non-reasoning model on the LFM3 backbone that sees images and video, hears audio and speaks back, including spoken questions about images, video with its soundtrack, and tool calls from what it sees and hears. Its provider-reported results stay separate from text-model rankings.
LFM3-Omni-2B sits in the LFM3 family with LFM3-1.7B, LFM3-Audio-2B, LFM3-1.7B-Base. Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated October 27, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does LFM3-Omni-2B perform overall in AI benchmarks?
LFM3-Omni-2B has published speech or voice results in Liquid AI LFM3 audio and omni evaluation. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Is LFM3-Omni-2B open source?
LFM3-Omni-2B is an open-weight model from LiquidAI. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to LFM3-Omni-2B?
LFM3-Omni-2B belongs to the LFM3 family. Related tracked variants include LFM3-1.7B, LFM3-Audio-2B, LFM3-1.7B-Base. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does LFM3-Omni-2B have full benchmark coverage on BenchLM?
No. LFM3-Omni-2B's speech or voice results appear in Liquid AI LFM3 audio and omni evaluation, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of LFM3-Omni-2B?
LFM3-Omni-2B has a documented context window of 32K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.