AI Agent StoreLiquid AI · Download verified
LFM3 Audio 2B
Build a local voice assistant that transcribes, translates, answers aloud or turns spoken requests into tool calls.
Released 2026-10-27 · First reviewed 2026-10-28 · Checked 2026-10-28.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Try it on your hardware and tasks before relying on it.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact download ID: LiquidAI/LFM3-Audio-2B. Accepts text and audio and returns text, speech or both. The card lists 18 speech languages. It is not recommended for complex coding or multi-step reasoning.
Downloadable under the LFM Open License v1.0, which limits commercial use by revenue. Review the full license for your organization. Use the model’s matching software and preprocessing; quality and device-speed claims on its card are publisher tests.
The card specifies 32K tokens across input and output. Other internal configuration lengths do not establish a larger supported conversation; a separate output maximum is not verified.
Running this download needs hardware, memory and maintenance. A model-specific hosted price and measured local operating cost are not established here.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗