Compare LLM Models

Select 2-5 models to compare side by side.

Select models to compare 0 / 5 selected

Top downloads

🤖 DeepSeek-V4-Pro-0813 deepseek-ai 🤖 GLM-5.3 zai-org 🤖 Kimi-K3 moonshotai

Select 2-5 models

Attribute	🤖 LFM2.5-VL-1.6B-Extract LiquidAI
Company	LiquidAI
Release Date	2026-05-26
Parameters (B)	1.6
Architecture	Hybrid conv+attention LFM2 with SigLIP2 vision encoder
Context Window	128000
Input Modalities	text, image
Open Source	Yes
License	other
Score	1
VRAM (GB)	4
Compute	Single NVIDIA GPU with 8 GB+ VRAM (e.g. L4, RTX 4090); ~4 GB for BF16 inference, GGUF/INT4 quantization for edge CPU deployment
Pricing (Input)	—
Pricing (Output)	—