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	🤖 medgemma-1.5-4b-it google
Company	google
Release Date	2026-01-13
Parameters (B)	4
Architecture	Decoder-only Transformer
Context Window	128000
Input Modalities	text, image
Open Source	Yes
License	other
Score	0
VRAM (GB)	16
Compute	NVIDIA GPU with 16GB+ VRAM for bf16 multimodal inference (e.g., T4); ~8-10GB with 4-bit quantization; 40GB+ recommended for QLoRA fine-tuning
Benchmark: MMLU-Pro	33.8
Pricing (Input)	—
Pricing (Output)	—