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-AWQ openbmb
Company	openbmb
Release Date	2026-05-11
Parameters (B)	1.3
Architecture	Transformer
Context Window	262144
Input Modalities	text, image, video
Open Source	Yes
License	apache-2.0
Score	4
VRAM (GB)	3
Compute	AWQ W4A16 quantized weights (~1.9GB); ~3GB GPU VRAM recommended. SigLIP2-400M vision encoder + Qwen3.5-0.8B LLM backbone; runs on consumer GPUs, supports vLLM/SGLang/Transformers, and deploys to iOS/Android/HarmonyOS edge devices.
Benchmark: MMMU	55.3
Benchmark: MMMU-Pro	33.5
Pricing (Input)	—
Pricing (Output)	—