LLM EXPLORER 56,604 MODELS INDEXED

SmolVLM2 2.2B Base by HuggingFaceTB

By HuggingFaceTB · 190 downloads
HF Repo ↗ Copy URL

SmolVLM2 2.2B Base is an open-source language model by HuggingFaceTB. Features: 2.2b LLM, VRAM: 4.5GB, License: apache-2.0, Instruction-Based.

  Arxiv:2504.05299 Base model:finetune:huggingfac... Base model:huggingfacetb/smolv...   Conversational Dataset:enxin/moviechat-1k tra... Dataset:huggingfacefv/finevide...   Dataset:huggingfacem4/docmatix Dataset:huggingfacem4/the caul... Dataset:lmms-lab/llava-onevisi... Dataset:lmms-lab/llava-video-1... Dataset:lmms-lab/m4-instruct-d... Dataset:mammoth-vl/mammoth-vl-...   Dataset:mutonix/vript   Dataset:orrzohar/video-star Dataset:sharegpt4video/sharegp...   Dataset:tiger-lab/vista-400k   En   Endpoints compatible   Idefics3   Image-text-to-text   Instruct   Region:us   Safetensors   Video-text-to-text
Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Base 

SmolVLM2 2.2B Base Parameters and Internals

LLM NameSmolVLM2 2.2B Base
Repository 🤗https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Base 
Base Model(s)  SmolVLM Base   HuggingFaceTB/SmolVLM-Base
Model Size2.2b
Required VRAM4.5 GB
Updated2026-08-09
MaintainerHuggingFaceTB
Model Typeidefics3
Instruction-BasedYes
Model Files  4.5 GB
Supported Languagesen
Model ArchitectureIdefics3ForConditionalGeneration
Licenseapache-2.0
Model Max Length8192
Transformers Version4.50.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49191
Torch Data Typebfloat16

Best Alternatives to SmolVLM2 2.2B Base

Best Alternatives
Context / RAM
Downloads
Likes
SmolVLM Instruct Bf160K / 4.5 GB445
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolVLM2-2.2B-Base.