Test it today on our playground by chatting with it! https://
playground.liquid.ai/talk
@maximelabonne
-
Test New AI Chat Tool on Liquid Playground Today
By
–
-
Model Achieves Faster Inference Speed Than Smaller Competitors
By
–
But the best feature is inference speed: it's significantly faster than models that are much smaller.
-
1.5B Parameter Model Achieves 56.8 VoiceBench Score
By
–
On VoiceBench, it scores 56.8 overall with just 1.5B parameters.
-
LFM2-1.2B Extension: Novel Audio Foundation Model Architecture
By
–
It has a super interesting architecture that extends LFM2-1.2B.
— Maxime Labonne @ ICLR (@maximelabonne) 1 octobre 2025
Unlike other audio foundation models, we disentangle the representations of audio input and output.
More info in the blog post. pic.twitter.com/cei9MSoCRuIt has a super interesting architecture that extends LFM2-1.2B. Unlike other audio foundation models, we disentangle the representations of audio input and output. More info in the blog post.
-
LFM2-Audio: 1.5B Multimodal Model 10x Faster Inference
By
–
LFM2-Audio just dropped!
— Maxime Labonne @ ICLR (@maximelabonne) 1 octobre 2025
It's a 1.5B model that understands and generates both text and audio
Inference 10x faster + quality on par with models 10x larger
Available today on @huggingface and our playground 🥳 pic.twitter.com/iJXWpyBCgqLFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on @huggingface and our playground
-
What Should Replace MMLU for AI Model Evaluation?
By
–
Final update! MMLU is saturated and has become (rightfully) less popular. What should replace it? – Other knowledge evals like GPQA, MMLU-Pro
– Code evals like LiveCodeBench
– Agentic evals like BFCL
– Other? -
LFM2-Extract Model Recommended for Extraction Tasks
By
–
They haven't been fine-tuned for this precise purpose, but I'd recommend checking LFM2-Extract (1.2B or 350M).
-
Models Available on Hugging Face with Multi-Framework Support
By
–
All the models are available on Hugging Face and compatible with Transformers, vLLM, llama.cpp, and ollama out of the box.
-
Math Model Training Recipe Released for v2
By
–
We released the entire training recipe for the Math model here (it's the same one we used for the v2):