lfm3-audio:2b-mlx-bf16

35 3 hours ago

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

tools audio 2b 
ollama run lfm3-audio:2b-mlx-bf16

Details

3 hours ago

d950f68bfdd8 ยท 4.2GB

json
{ "architectures": [ "Lfm3AudioForConditionalGeneration" ], "model_type": "lfm3_audio", "format_vers
json
{ "bos_token_id": 124894, "eos_token_id": [124900, 125014], "pad_token_id": 124893, "use_cache": tru
json
{ "encoder_stride": 8, "feature_extractor_type": "Lfm3AudioFeatureExtractor", "feature_size": 128, "
json
{ "audio_out_token": "<|audio_out|>", "audio_token": "<|audio|>", "feature_extractor": { "encoder_st
json
{ "bos_token": "<|startoftext|>", "eos_token": "<|im_end|>", "pad_token": "<|pad|>" }
json
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 124893, "content"
json
{ "backend": "tokenizers", "bos_token": "<|startoftext|>", "eos_token": "<|im_end|>", "extra_special
json
{ "transformers_version": "5.19.0.dev0", "architectures": [ "LiquidCodecModel" ], "output_hidden_sta
license
LFM Open License v1.0 TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "
params
{ "temperature": 0 }
742 tensors

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.