microsoft/Phi-3.5-vision-instruct download history

microsoft/Phi-3.5-vision-instruct is a 4.1B-parameter image text to text model by microsoft. In the last 30 days it was downloaded 257,092 times (70,467 in the last 7 days), and 20,985,331 times in total.

It ranks #1,257 on the Hub by monthly downloads and #206 among image text to text models.

It has 750 likes.

35 models build on Phi-3.5-vision-instruct: 14 quantized, 18 fine-tuned, 3 adapters and 0 merges. Together with the original they were downloaded 269,069 times in the last 30 days. See the Phi-3.5-vision-instruct galaxy.

Most downloaded derivatives

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-18257,092-23%
October 2026332,496-59%
September 2026815,247+4%
August 2026782,917-38%
July 20261,261,702-10%
June 20261,405,917-30%
May 20261,994,758+21%
April 20261,649,669+30%
March 20261,265,584+117%
February 2026583,139-22%
January 2026748,343+33%
December 2025560,598+31%

Its busiest 30 days so far ended on 2026-06-11, with 2,006,050 downloads.

Open microsoft/Phi-3.5-vision-instruct on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.