Skip to content
Local AI Wizard
Your machine
Theme

SmolVLM-Instruct

Hugging Face · HuggingFaceTB/SmolVLM-Instruct

Weights license: Apache 2.0 · code and components may use other terms

Reported by the publisher6 resultsHugging Face's model card · read 2026-10-25 · not ranked · see them
Memory needed~2 GBQ4 weights + working room, before the machine's reserve
Parameters2.2 BHub safetensors total
Repository updated2025-04-08A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

6 results · Hugging Face's model card · read 2026-10-25
MMMU (val)
38.8
MathVista (testmini)
44.6
MMStar (val)
42.1
DocVQA (test)
81.6
TextVQA (val)
72.7
Min GPU RAM required (GB)
5.02

Values as printed on the card, with the publisher's own settings (card section: Evaluation); column “SmolVLM”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 119

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 119

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Consider it for

Hugging Face released SmolVLM-Instruct on 2024-11-26: a vision-language model that answers about images, with 2.2B parameters on the Hugging Face count and the Apache 2.0 license. Languages the publisher declares: en.

Check first

License: commercial use allowed. At Q4 the weights load about 1.7 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Transformers · model card · How to get started
import torch
from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

# Load images
image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
image2 = load_image("https://huggingface.co/spaces/merve/chameleon-7b/resolve/main/bee.jpg")

# Initialize processor and model
processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-Instruct")
model = AutoModelForVision2Seq.from_pretrained(
    "HuggingFaceTB/SmolVLM-Instruct",
    torch_dtype=torch.bfloat16,
    _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
).to(DEVICE)

# Create input messages
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "image"},
            {"type": "text", "text": "Can you describe the two images?"}
        ]
    },
]

# Prepare inputs
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
inputs = inputs.to(DEVICE)

# Generate outputs
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)

print(generated_texts[0])
"""
Assistant: The first image shows a green statue of the Statue of Liberty standing on a stone pedestal in front of a body of water. 
The statue is holding a torch in its right hand and a tablet in its left hand. The water is calm and there are no boats or other objects visible. 
The sky is clear and there are no clouds. The second image shows a bee on a pink flower. 
The bee is black and yellow and is collecting pollen from the flower. The flower is surrounded by green leaves.
"""

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
image-text-to-text
Architecture
Idefics3ForConditionalGeneration
Library in source
transformers
Weight license
Apache 2.0HuggingFaceTB/SmolVLM-Instruct model card (Hugging Face) · read 2026-10-18source
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Languages
enModel card metadata · read 2026-10-25source
Released
SmolVLM blog post (Hugging Face blog; date from huggingface/blog _blog.yml entry 'smolvlm') · read 2026-10-18source
Every stored field12 fields
Revision checked
81cd9a775a4d644f2faf4e7becff4559b46b14c7
Architecture
Idefics3ForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Declared base models
HuggingFaceTB/SmolLM2-1.7B-Instruct · google/siglip-so400m-patch14-384
Formats
transformers, onnx, safetensors
Access
Open download
Publisher kind
Official
Repository created
2024-11-18creation is not the model's release
Repository updated
2025-04-08a commit is not a release date
Hub downloads (30 days) · likes
15,879 · 601this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.