lfm3-audio

19 Downloads Updated an hour ago

LFM3-Audio-2B is a compact, fully featured audio model.

tools audio 2b

ollama run lfm3-audio

curl http://localhost:11434/api/chat \
  -d '{
    "model": "lfm3-audio",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='lfm3-audio',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'lfm3-audio',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model lfm3-audio

OpenCode

OpenCode ollama launch opencode --model lfm3-audio

Hermes Agent

Hermes Agent ollama launch hermes --model lfm3-audio

OpenClaw

OpenClaw ollama launch openclaw --model lfm3-audio

Models

Name

5 models

Size / Usage

Context

Input

lfm3-audio:latest

2.1GB · - context window · Text · an hour ago

lfm3-audio:latest

2.1GB

-

Text

lfm3-audio:2b

2.1GB · - context window · Text · an hour ago

lfm3-audio:2b latest

2.1GB

-

Text

Readme

LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.

Voice chat: ask questions aloud and receive streaming replies in text and speech. For text-only responses, the model can reason before answering.
Multilingual speech: transcribe, synthesize, and translate speech across 18 languages.
Audio understanding and reasoning: interpret recordings and answer questions about the speech, sounds, and events they contain.
Tool calling: turn spoken requests into tool calls to control apps and devices, with text or speech alongside the calls.

LFM3-Audio-2B introduces an in-house audio encoder and LiquidCodec audio tokenizer, improving speech quality over LFM2.5-Audio.

Model details

The LFM3 family includes base, text, vision, audio, omni, and decision models.

Property	Specification
Parameters	2B total
Architecture	LFM3 backbone, causal audio encoder, and LiquidCodec audio tokenizer
Input	Text or audio; audio encoder operates at 16 kHz
Output	Text, 24 kHz speech, or interleaved text and speech
Context length	32K tokens (input + output)
Streaming	Causal audio encoding, incremental prefill, and streaming speech generation
Speech languages / locales	Arabic, Danish, German, Greek, British English, American English, Finnish, French, Hebrew, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Spanish, Swedish, Turkish, Chinese
License	LFM Open License v1.0

LFM3-Audio-2B is designed for local agents, tool calling, structured outputs, and domain-specific fine-tuning. Use retrieval or search for knowledge-heavy tasks. It is not recommended for agentic coding or complex multi-step reasoning due to its small size.

LFM3-Audio-2B is a **compact, fully featured audio model that runs locally on laptops and edge devices.** It takes text or audio as input and responds with text, speech, or both.

* **Voice chat:** ask questions aloud and receive streaming replies in text and speech. For text-only responses, the model can reason before answering.
* **Multilingual speech:** transcribe, synthesize, and translate speech across 18 languages.
* **Audio understanding and reasoning:** interpret recordings and answer questions about the speech, sounds, and events they contain.
* **Tool calling:** turn spoken requests into tool calls to control apps and devices, with text or speech alongside the calls.

LFM3-Audio-2B introduces an in-house audio encoder and LiquidCodec audio tokenizer, improving speech quality over LFM2.5-Audio.

# Model details
The LFM3 family includes base, text, vision, audio, omni, and decision models.

| Property | Specification |
|:--- |:---:|
| Parameters | 2B total |
| Architecture |  LFM3 backbone, causal audio encoder, and LiquidCodec audio tokenizer
| Input | Text or audio; audio encoder operates at 16 kHz
| Output | Text, 24 kHz speech, or interleaved text and speech
| Context length|   32K tokens (input + output)
| Streaming | Causal audio encoding, incremental prefill, and streaming speech generation
| Speech languages / locales | Arabic, Danish, German, Greek, British English, American English, Finnish, French, Hebrew, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Spanish, Swedish, Turkish, Chinese
| License |     LFM Open License v1.0
LFM3-Audio-2B is designed for local agents, tool calling, structured outputs, and domain-specific fine-tuning. Use retrieval or search for knowledge-heavy tasks. It is not recommended for agentic coding or complex multi-step reasoning due to its small size.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)