SmolVLM-Instruct
Hugging Face · HuggingFaceTB/SmolVLM-Instruct
Weights license: Apache 2.0 · code and components may use other terms
Quality
No comparable score
We track no public, comparable benchmark that covers this model yet. No score is inferred.
Reported by the publisher
- 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.
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.
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.
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.
"""Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- HuggingFaceTB/SmolVLM-Instruct
- 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 field
- 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.
- Publisher model card
- License: HuggingFaceTB/SmolVLM-Instruct model card (Hugging Face)
- Release date: SmolVLM blog post (Hugging Face blog; date from huggingface/blog _blog.yml entry 'smolvlm')
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.






























































