All tasks / Models
LFM2.5-Audio-1.5B
Liquid AI's small open-weights end-to-end audio model for on-device voice chat, ASR and TTS.
- Liquid AI
- Open weights
- Released 18 Dec 2025
Where it ranks
- –Voice agentsModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- Liquid AI
- Family
- LFM Audio
- Released
- 18 Dec 2025
- Weights
- Open: download and run it yourself
- License
- LFM Open License v1.0
- Parameters
- 1.47B
- GPU memory to run locally
- ~4 GB (Derived: about 1.47B parameters is roughly 2.9 GB of bf16 weights plus runtime overhead; not an official requirement.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Benchmark results
No public benchmark results recorded yet.
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.