LiquidAI/LFM3-Omni-2B-GGUF
AI model · https://huggingface.co/LiquidAI/LFM3-Omni-2B-GGUF
First seen by Oriel on .
AI summary
This Hugging Face page provides a GGUF version of LFM3-Omni-2B for on-device CPU and GPU inference across text, image, video, and audio inputs, with text and speech output.
- LFM3-Omni-2B is an omni-modal, non-reasoning model designed for local use on devices.
- llama.cpp supports image, audio, video, speech synthesis, and real-time voice conversations with tool calls through its /v1/realtime WebSocket API.
- Llama.app, LM Studio, and Ollama provide varying platform and modality support, with specific minimum versions listed.
- The llama.cpp examples cover speech recognition, image and video understanding, text-to-speech, and OpenAI-compatible serving.
- Recommended settings are temperature 0 for text, audio temperature 0.4, and audio repetition penalty 1.2 for speech output.
#gguf #multimodal models #llama.cpp #on-device ai
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Likes
Total likes reported by the source.
- Hugging Face Models: 120, latest observation ; +12 over observed period since
Downloads (30d)
Rolling 30-day downloads. A change in this value is not new downloads during the observed period.
- Hugging Face Models: 167,804, latest observation ; +35,589 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Models | LiquidAI/LFM3-Omni-2B-GGUF | https://huggingface.co/LiquidAI/LFM3-Omni-2B-GGUF Read discussion |