Liquid AI
Liquid: Playground
# LFM2-1.2B-NVFP4A16

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2-1.2B

🏃 How to run LFM2 (NVFP4A16)

Require Blackwell GPU and vllm:

vllm serve apolloparty/LFM2-12B-NVFP4A16
Downloads last month
-
Safetensors
Model size
717M params
Tensor type
F32
·
BF16
·
F8_E4M3
·
U8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for apolloparty/LFM2-1.2B-NVFP4A16

Base model

LiquidAI/LFM2-1.2B
Quantized
(7)
this model

Collection including apolloparty/LFM2-1.2B-NVFP4A16