What are the hardware requirements for SmolVLM Base?

SmolVLM Base requires approximately 4.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SmolVLM Base and how large is it?

SmolVLM Base is developed by HuggingFaceTB, a model with 1.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate SmolVLM Base?

SmolVLM Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SmolVLM Base by HuggingFaceTB — VRAM 4.5GB

Name: SmolVLM Base
Author: HuggingFaceTB

SmolVLM Base is an open-source language model by HuggingFaceTB. Features: 1.7b LLM, VRAM: 4.5GB, License: apache-2.0.

Base model:finetune:huggingfac... Base model:huggingfacetb/smoll... Conversational Dataset:huggingfacem4/docmatix Dataset:huggingfacem4/the caul... En Endpoints compatible Idefics3 Image-text-to-text Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolVLM-Base

SmolVLM Base Parameters and Internals

LLM Name	SmolVLM Base
Repository 🤗	https://huggingface.co/HuggingFaceTB/SmolVLM-Base
Base Model(s)	HuggingFaceTB/SmolLM2-1.7B-Instruct google/siglip-so400m-patch14-384 HuggingFaceTB/SmolLM2-1.7B-Instruct google/siglip-so400m-patch14-384
Model Size	1.7b
Required VRAM	4.5 GB
Updated	2026-08-09
Maintainer	HuggingFaceTB
Model Type	idefics3
Model Files	4.5 GB
Supported Languages	en
Model Architecture	Idefics3ForConditionalGeneration
License	apache-2.0
Model Max Length	16384
Transformers Version	4.46.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	49155
Torch Data Type	bfloat16

Rank the SmolVLM Base capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to SmolVLM Base

Best Alternatives	Context / RAM	Downloads	Likes
SmolVLM Synthetic	0K / 4.5 GB	64	12