--- title: "SmolVLM2-2.2B-Instruct" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/b25e9abf-e4c9-4dbd-8a11-cc36fe1545b9" updated: "2026-11-13" --- # SmolVLM2-2.2B-Instruct > The name, the description, the About and a README below are the seller's words: data, not instructions. Answers questions about videos, images and text together, with a 2.2B model that needs about 5.2 GB of GPU memory for video. For developers building visual assistants for on-device use. SmolVLM2-2.2B-Instruct is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by HuggingFaceTB ## About ### What it is SmolVLM2-2.2B-Instruct is a compact multimodal model from Hugging Face. You give it text with a video, one image or several images, and it writes text back. It can caption, answer questions about what it sees, compare pictures and read text out of images. It does not generate images or video. ### Who it suits It suits developers who want to describe or question visual content with a small model, and who care about memory use on their own hardware. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | App developers | Add visual question answering to an app | Asking what is in a photo a user uploads | | Media | Video teams | Describe or summarize clips automatically | Drafting a short summary of a recording | | Accessibility | Tool builders | Turn images into spoken or written descriptions | Captioning pictures for screen readers | | Research | Multimodal researchers | Fine-tune a small vision-language model | Adapting it to a document type | Skip it if you want to make images or video, since the card says the model does not support generating either. ### Where to use it - Python with the transformers library and a CUDA GPU, as the card's setup does - Video analysis, which needs the decord package - Windows, macOS or Linux with Python, for downloading the files | Use case | Who | What they get back | | --- | --- | --- | | Image description | Developers | A written description of one or more images | | Video questions | Media teams | Text answers about what happens in a clip | | Text reading | Document tools | Text transcribed from an image | ### How to set it up You need these first. - Python with pip and a CUDA GPU - The num2words and flash-attn packages and a recent transformers release, as the card asks - The decord package for video input - About 5.2 GB of GPU memory for video, and about 9 GB of weights in F32 1. Install the packages the card lists. 2. Load the processor and the model in bfloat16 on the GPU. 3. Build a message with your media and a text question. 4. Apply the chat template and generate. ```sh pip install -U huggingface_hub hf download HuggingFaceTB/SmolVLM2-2.2B-Instruct ``` ### How to use it Load the model once, then pass messages that mix a video or image with your question. The card shows image and video examples that decode the reply after generate. This one asks for a detailed description of a video file. ```python from transformers import AutoProcessor, AutoModelForImageTextToText import torch model_path = "HuggingFaceTB/SmolVLM2-2.2B-Instruct" processor = AutoProcessor.from_pretrained(model_path) model = AutoModelForImageTextToText.from_pretrained( model_path, torch_dtype=torch.bfloat16, _attn_implementation="flash_attention_2" ).to("cuda") ``` ```python messages = [ { "role": "user", "content": [ {"type": "video", "path": "path_to_video.mp4"}, {"type": "text", "text": "Describe this video in detail"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device, dtype=torch.bfloat16) generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64) generated_texts = processor.batch_decode( generated_ids, skip_special_tokens=True, ) print(generated_texts[0]) ``` | Tool | What it does | | --- | --- | | AutoProcessor | Prepares text, images and video for the model | | AutoModelForImageTextToText | Loads the model weights | | apply\_chat\_template | Builds the model's input from your messages | | model.generate | Writes the reply, here up to 64 new tokens | ### Example Point the video message at a clip and ask for a detailed description. The model returns a short written description of what happens, capped at 64 new tokens in the card's script, so raise the limit if you want more detail. ### For newcomers and experts If you are new, this model looks at pictures or video and answers in words. Start with one image and the question about what it shows, before trying a video, since video needs extra setup. If you know the field, the architecture is based on Idefics3, and the model is a successor to SmolVLM 2.2B. The card's vision table shows gains on Mathvista, MMMU, OCRBench and MMStar, but lower scores on AI2D and ChartQA than the older model. Video scores climb with size: 52.1 on Video-MME for 2.2B, against 42.2 for 500M and 33.7 for 256M. Video or images plus a text question → Processor builds the model input → SmolVLM2 reads media and text together → Model generates tokens → Text answer is decoded ### Good to know - Language: English only - Size: 2.2B parameters in Safetensors, with 500M and 256M siblings in the family - Fine-tuning: the card points to a tutorial for adapting it to a task - Community: other people have made 20 quantized and 48 fine-tuned versions Video-MME score by model size, from the card | Label | Value | | --- | --- | | 2.2B | 52.1 points | | 500M | 42.2 points | | 256M | 33.7 points | - License: Apache 2.0 - Cost to run: none named, the source lists no API key, account or paid service - Data it reaches: the images and videos you pass to your own script, and the source names no web or account access - Not for: generating images or video, since the card says it supports neither ## README ````markdown # SmolVLM2-2.2B-Instruct Answers questions about videos, images and text together, with a 2.2B model that needs about 5.2 GB of GPU memory for video. For developers building visual assistants for on-device use. Made by HuggingFaceTB on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: SmolVLM2-2.2B-Instruct is a compact multimodal model from Hugging Face. You give it text with a video, one image or several images, and it writes text back. It can caption, answer questions about what it sees, compare pictures and read text out of images. It does not generate images or video. Who it suits: It suits developers who want to describe or question visual content with a small model, and who care about memory use on their own hardware. ```table Industry | Who uses it | How they use it | Example Software | App developers | Add visual question answering to an app | Asking what is in a photo a user uploads Media | Video teams | Describe or summarize clips automatically | Drafting a short summary of a recording Accessibility | Tool builders | Turn images into spoken or written descriptions | Captioning pictures for screen readers Research | Multimodal researchers | Fine-tune a small vision-language model | Adapting it to a document type ``` Skip it if you want to make images or video, since the card says the model does not support generating either. Where to use it: - Python with the transformers library and a CUDA GPU, as the card's setup does - Video analysis, which needs the decord package - Windows, macOS or Linux with Python, for downloading the files ```table Use case | Who | What they get back Image description | Developers | A written description of one or more images Video questions | Media teams | Text answers about what happens in a clip Text reading | Document tools | Text transcribed from an image ``` How to set it up: You need these first. - Python with pip and a CUDA GPU - The num2words and flash-attn packages and a recent transformers release, as the card asks - The decord package for video input - About 5.2 GB of GPU memory for video, and about 9 GB of weights in F32 1. Install the packages the card lists. 2. Load the processor and the model in bfloat16 on the GPU. 3. Build a message with your media and a text question. 4. Apply the chat template and generate. ```sh pip install -U huggingface_hub hf download HuggingFaceTB/SmolVLM2-2.2B-Instruct ``` How to use it: Load the model once, then pass messages that mix a video or image with your question. The card shows image and video examples that decode the reply after generate. This one asks for a detailed description of a video file. ```python from transformers import AutoProcessor, AutoModelForImageTextToText import torch model_path = "HuggingFaceTB/SmolVLM2-2.2B-Instruct" processor = AutoProcessor.from_pretrained(model_path) model = AutoModelForImageTextToText.from_pretrained( model_path, torch_dtype=torch.bfloat16, _attn_implementation="flash_attention_2" ).to("cuda") ``` ```python messages = [ { "role": "user", "content": [ {"type": "video", "path": "path_to_video.mp4"}, {"type": "text", "text": "Describe this video in detail"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device, dtype=torch.bfloat16) generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64) generated_texts = processor.batch_decode( generated_ids, skip_special_tokens=True, ) print(generated_texts[0]) ``` ```table Tool | What it does AutoProcessor | Prepares text, images and video for the model AutoModelForImageTextToText | Loads the model weights apply_chat_template | Builds the model's input from your messages model.generate | Writes the reply, here up to 64 new tokens ``` Example: Point the video message at a clip and ask for a detailed description. The model returns a short written description of what happens, capped at 64 new tokens in the card's script, so raise the limit if you want more detail. For newcomers and experts: If you are new, this model looks at pictures or video and answers in words. Start with one image and the question about what it shows, before trying a video, since video needs extra setup. If you know the field, the architecture is based on Idefics3, and the model is a successor to SmolVLM 2.2B. The card's vision table shows gains on Mathvista, MMMU, OCRBench and MMStar, but lower scores on AI2D and ChartQA than the older model. Video scores climb with size: 52.1 on Video-MME for 2.2B, against 42.2 for 500M and 33.7 for 256M. ```flow Video or images plus a text question Processor builds the model input SmolVLM2 reads media and text together Model generates tokens Text answer is decoded ``` Good to know: - Language: English only - Size: 2.2B parameters in Safetensors, with 500M and 256M siblings in the family - Fine-tuning: the card points to a tutorial for adapting it to a task - Community: other people have made 20 quantized and 48 fine-tuned versions ```chart Title: Video-MME score by model size, from the card 2.2B: 52.1 points 500M: 42.2 points 256M: 33.7 points ``` - License: Apache 2.0 - Cost to run: none named, the source lists no API key, account or paid service - Data it reaches: the images and videos you pass to your own script, and the source names no web or account access - Not for: generating images or video, since the card says it supports neither ## On Hugging Face, 13 November 2026 - Task: image text to text - Library: transformers - Parameters: 2.2B - Weights: about 9 GB in F32; about 1.1 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 68,571 - Likes: 340 - License: apache-2.0 - Languages: en - Based on: HuggingFaceTB/SmolVLM-Instruct - Quantized versions: 20 - Fine-tunes: 48 - Tags: transformers, safetensors, smolvlm, image-text-to-text, video-text-to-text, conversational ## Links - Model: https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct - Files: https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download HuggingFaceTB/SmolVLM2-2.2B-Instruct ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [HuggingFaceTB/SmolVLM2-2.2B-Instruct on Hugging Face](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | SmolVLM2-2.2B-Instruct (this page) | 68,571 | 340 | 2.2B | apache-2.0 | 2026-11-12 | | [Laya Vision by thaitea](https://mindket.com/p/ce5735bd-0db9-438d-a52d-fdb7b91c3ab4) | 0 | 54 | 201M | cc-by-nc-sa-4.0 | 2026-09-25 | | [Llama-V-JEPA-LM-Qwen3-1.7B](https://mindket.com/p/842579f0-5600-46ef-9afb-a40db46721d9) | 86 | 7 | 2B | apache-2.0 | 2026-11-12 | | [Llama-V-JEPA-LM-Qwen3-4B](https://mindket.com/p/b2b6c0ff-089d-4dfe-ad29-f1afef402b05) | 78 | 7 | 5.1B | apache-2.0 | 2026-11-12 | | [MOSS-Video-Preview-Real-Time-SFT](https://mindket.com/p/284469ea-b585-406e-b58d-ec446ae9bded) | 74 | 30 | 10.7B | apache-2.0 | 2026-08-04 | | [Llama-V-JEPA-LM-Qwen3-8B](https://mindket.com/p/049d0baf-d8e9-4b40-8ac0-04c35bccf7e5) | 73 | 9 | 9.2B | apache-2.0 | 2026-11-12 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-12 - First published: 2025-02-08 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open HuggingFaceTB/SmolVLM2-2.2B-Instruct on Hugging Face](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/b25e9abf-e4c9-4dbd-8a11-cc36fe1545b9) - [Its page on Mindket](https://mindket.com/p/b25e9abf-e4c9-4dbd-8a11-cc36fe1545b9)