liquidai/lfm2.5-audio-1.5b-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "license_name": "lfm1.0",
    "license_link": "LICENSE",
    "language": [
      "en"
    ],
    "tags": [
      "liquid",
      "lfm2.5",
      "edge",
      "llama.cpp",
      "audio",
      "speech",
      "gguf"
    ],
    "base_model": [
      "LiquidAI/LFM2.5-Audio-1.5B"
    ],
    "widget": [
      {
        "text": "Demo",
        "output": {
          "url": "https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B-GGUF/resolve/main/demo.mp4"
        }
      }
    ],
    "frontmatter": {
      "license": "other",
      "license_name": "lfm1.0",
      "license_link": "LICENSE",
      "language": [
        "en"
      ],
      "tags": [
        "liquid",
        "lfm2.5",
        "edge",
        "llama.cpp",
        "audio",
        "speech",
        "gguf"
      ],
      "base_model": [
        "LiquidAI/LFM2.5-Audio-1.5B"
      ],
      "widget": [
        "text: \"Demo\""
      ]
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png",
    "summary": "Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlicense_name: lfm1.0\nlicense_link: LICENSE\nlanguage:\n- en\ntags:\n- liquid\n- lfm2.5\n- edge\n- llama.cpp\n- audio\n- speech\n- gguf\nbase_model:\n- LiquidAI/LFM2.5-Audio-1.5B\nwidget:\n  - text: \"Demo\"\n    output:\n      url: demo.mp4\n---\n\n<div align=\"center\">\n  <img\n    src=\"https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png\"\n    alt=\"Liquid AI\"\n    style=\"width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;\"\n  />\n  <div style=\"display: flex; justify-content: center; gap: 0.5em;\">\n<a href=\"https://playground.liquid.ai/\"><strong>Try LFM</strong></a> • <a href=\"https://docs.liquid.ai/lfm/getting-started/welcome\"><strong>Docs</strong></a> • <a href=\"https://leap.liquid.ai/\"><strong>LEAP</strong></a> • <a href=\"https://discord.com/invite/liquid-ai\"><strong>Discord</strong></a>\n  </div>\n</div>\n\n<br>\n\n# LFM2.5-Audio-1.5B\n\nFind more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B\n\n## Runners\n\n`runners` folder contains runners for various architectures including\n\n- llama-liquid-audio-cli\n- llama-liquid-audio-server\n\n# 🏃 How to run LFM2.5\n\n## CLI\n\nSet env variables.\n```\nexport CKPT=/path/to/LFM2.5-Audio-1.5B-GGUF\nexport INPUT_WAV=/path/to/input.wav\nexport OUTPUT_WAV=/path/to/output.wav\n```\n\n### ASR (audio -> text)\n\n```bash\n./llama-liquid-audio-cli -m $CKPT/LFM2.5-Audio-1.5B-Q4_0.gguf -mm $CKPT/mmproj-LFM2.5-Audio-1.5B-Q4_0.gguf -mv $CKPT/vocoder-LFM2.5-Audio-1.5B-Q4_0.gguf --tts-speaker-file $CKPT/tokenizer-LFM2.5-Audio-1.5B-Q4_0.gguf -sys \"Perform ASR.\" --audio $INPUT_WAV\n```\n\n### TTS (text -> audio)\n\n```bash\n./llama-liquid-audio-cli -m $CKPT/LFM2.5-Audio-1.5B-Q4_0.gguf -mm $CKPT/mmproj-LFM2.5-Audio-1.5B-Q4_0.gguf -mv $CKPT/vocoder-LFM2.5-Audio-1.5B-Q4_0.gguf --tts-speaker-file $CKPT/tokenizer-LFM2.5-Audio-1.5B-Q4_0.gguf -sys \"Perform TTS.\" -p \"Hi, how are you?\" --output $OUTPUT_WAV\n```\n\n### Interleaved (audio/text -> audio + text)\n\n```bash\n./llama-liquid-audio-cli -m $CKPT/LFM2.5-Audio-1.5B-Q4_0.gguf -mm $CKPT/mmproj-LFM2.5-Audio-1.5B-Q4_0.gguf -mv $CKPT/vocoder-LFM2.5-Audio-1.5B-Q4_0.gguf --tts-speaker-file $CKPT/tokenizer-LFM2.5-Audio-1.5B-Q4_0.gguf -sys \"Respond with interleaved text and audio.\" --audio $INPUT_WAV --output $OUTPUT_WAV\n```\n\n\n## Server\n\nStart server\n```\nexport CKPT=/path/to/LFM2.5-Audio-1.5B-GGUF\n./llama-liquid-audio-server -m $CKPT/LFM2.5-Audio-1.5B-Q4_0.gguf -mm $CKPT/mmproj-LFM2.5-Audio-1.5B-Q4_0.gguf -mv $CKPT/vocoder-LFM2.5-Audio-1.5B-Q4_0.gguf --tts-speaker-file $CKPT/tokenizer-LFM2.5-Audio-1.5B-Q4_0.gguf\n```\n\nUse `liquid_audio_chat.py` script to communicate with the server.\n\n```bash\nuv run liquid_audio_chat.py\n```\n\n# Source Code for Runners\n\nRunners are built from https://github.com/ggml-org/llama.cpp/pull/18641. It's WIP and will take time to land in upstream.\n\n# Demo\n\n<Gallery />\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "liquid",
    "lfm2.5",
    "edge",
    "llama.cpp",
    "audio",
    "speech",
    "en",
    "base_model:LiquidAI/LFM2.5-Audio-1.5B",
    "base_model:quantized:LiquidAI/LFM2.5-Audio-1.5B",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 91,
  "downloads": 14621,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-30T13:27:35.000Z",
  "created_at": "2026-01-06T01:39:14.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "695c67c2af2a8d1d8e300dd5",
  "id": "LiquidAI/LFM2.5-Audio-1.5B-GGUF",
  "modelId": "LiquidAI/LFM2.5-Audio-1.5B-GGUF",
  "sha": "7d525f883a077e20afb782f2ff618edcae0e39e4",
  "createdAt": "2026-01-06T01:39:14.000Z",
  "lastModified": "2026-03-30T13:27:35.000Z",
  "author": "LiquidAI",
  "downloads": 14621,
  "likes": 91,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}