All models

LFM2.5-Audio-1.5B

byLiquid AILiquid AI· 18 Dec 2025
MultimodalAudio generation

Liquid continued pretraining from 10T (of their 2.0 series) to 28T tokens and it shows! This model update really surprised us: In our vibe testing, it came very close to Qwen3 4B 2507 Instruct, which we use every day. And this model is over 3 times smaller! In a direct comparison against the (still bigger) Qwen3 1.6B, we preferred LFM2.5 basically every time. And this time, they released all the other variants at once, i.e., a Japanese version, a vision and an audio model.

Specs
Params1.5B
LicenseLFM Open License v1.0
Tags
modelsmodels/llms/multi-modalmodels/audio-generationartifacts/18
Adoption · Interconnects
RAM score
Hugging Face Downloads
1.5K
last 30d
8.8K
all time
HF Likes
434

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models