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	🤖 MiniCPM-V-4.6-Thinking openbmb
Company	openbmb
Release Date	2026-05-11
Parameters (B)	1.3
Architecture	Multimodal Transformer (SigLIP2 + Qwen3.5)
Context Window	262144
Input Modalities	text, image
Open Source	Yes
License	apache-2.0
Score	4
VRAM (GB)	4
Compute	~4GB GPU VRAM for BF16 inference; ~3GB with INT4 quantization (AWQ/BNB/GPTQ); Q4_K_M GGUF ~2GB on CPU; runs on consumer GPUs and mobile devices (iOS/Android/HarmonyOS)
Benchmark: MMMU	55.3
Benchmark: MMMU-Pro	33.5
Pricing (Input)	—
Pricing (Output)	—