SmolVLM-500M-Instruct

HuggingFaceTB/SmolVLM-500M-Instruct

Image Text to Text507M parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 3, 2026View on Hugging Face ↗
Downloads 30D
150.9K
Total downloads
2.1M
Gained 7D
+45.1K(increase)
2.3%(up) vs baseline
Gained 30D
—
Likes
198
+2 in 7D
Rank · tracked models
#1,895
5(up 5 places)this week
Parameters
507M
Last source update
Apr 8, 2025
Momentum
89.1
  • SmolVLM-500M-Instruct gained 45.1K downloads during the last seven tracked days.
  • It moved from #300 to #306 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

SmolVLM-500M-Instruct is a image text to text model published by HuggingFaceTB. OpenModelStats has tracked the model since Sep 3, 2026, most recently observing it Oct 3, 2026.

Published
Jan 20, 2025
Last updated
Apr 8, 2025
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
507,482,304
Spaces
—
Derivative models
2
Velocity 7D/day
6,449
transformersonnxsafetensorsidefics3image-text-to-textconversationalendataset:HuggingFaceM4/the_cauldrondataset:HuggingFaceM4/Docmatixarxiv:2504.05299base_model:HuggingFaceTB/SmolLM2-360M-Instructbase_model:quantized:HuggingFaceTB/SmolLM2-360M-Instruct

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

Models similar to SmolVLM-500M-Instruct
ModelDL 30D
SmolVLM2-500M-Video-InstructHuggingFaceTB1.2M
SmolVLM-500M-BaseHuggingFaceTB384
VisionPsy-Nano-460M-Flashqvac900
VisionPsy-Nano-460Mqvac597
gemma-4-31B-it-qat-q4_0-unquantized-assistantgoogle35.8K
GOT-OCR-2.0-hfstepfun-ai48.8K
HuggingFaceTB/SmolVLM-500M-Instruct — Downloads, Growth & Stats | OpenModelStats