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	🤖 Cosmos-Reason1-7B nvidia
Company	nvidia
Release Date	2025-05-17
Parameters (B)	7
Architecture	Vision-Language Transformer
Context Window	128000
Input Modalities	text, image
Open Source	Yes
License	other
Score	0
VRAM (GB)	16
Compute	NVIDIA GPU with ≥16GB VRAM (A100, H100, or GB200 recommended) for BF16 inference on Linux with CUDA; 4-bit quantization possible on ~8GB VRAM
Pricing (Input)	—
Pricing (Output)	—