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	🤖 SmolVLM-Instruct HuggingFaceTB
Company	HuggingFaceTB
Release Date	2024-11-26
Parameters (B)	2
Architecture	Vision-Language Transformer (Idefics3)
Context Window	16000
Input Modalities	text, image
Open Source	Yes
License	apache-2.0
Score	0
VRAM (GB)	5.0
Compute	Runs inference with ~5 GB GPU VRAM in bfloat16; supports Flash Attention 2 on CUDA and 4/8-bit quantization via bitsandbytes or torchao for lower-memory deployment on consumer GPUs or laptops.
Benchmark: MMMU	38.8
Pricing (Input)	—
Pricing (Output)	—