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-3.2-90B-Vision-Instruct meta-llama
Company	meta-llama
Release Date	2024-09-25
Parameters (B)	90
Architecture	Transformer
Context Window	128000
Input Modalities	text, image
Open Source	Yes
License	llama3.2
Score	6
VRAM (GB)	60
Compute	Minimum ~60GB VRAM with Q4_K_M quantization; ~180GB VRAM for BF16 inference (2x A100 80GB or H100 recommended)
Benchmark: GPQA	46.1
Benchmark: GSM8K	93.1
Pricing (Input)	—
Pricing (Output)	—