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	🤖 Llama-3.1-Nemotron-Nano-VL-8B-V1 nvidia
Company	nvidia
Release Date	2025-06-03
Parameters (B)	9
Architecture	Transformer
Context Window	16384
Input Modalities	text, image
Open Source	Yes
License	other
Score	0
VRAM (GB)	24
Compute	NVIDIA GPU with CUDA; TensorRT-LLM runtime; tested on 1× H100 SXM 80GB; AWQ 4-bit quantization enables edge deployment on Jetson Orin and laptops via TinyChat
Benchmark: MMMU	48.2
Pricing (Input)	—
Pricing (Output)	—