meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 download history

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 is a 401.6B-parameter image text to text model by meta-llama. In the last 30 days it was downloaded 27,355 times (442 in the last 7 days), and 1,743,115 times in total.

It ranks #5,153 on the Hub by monthly downloads and #677 among image text to text models.

It has 189 likes, 1 of them in the last week.

It is a quantization of meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8.

3 models build on Llama-4-Maverick-17B-128E-Instruct-FP8: 3 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 27,458 times in the last 30 days. See the Llama-4-Maverick-17B-128E-Instruct-FP8 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 2026-11-1827,355-35%
October 202642,408-13%
September 202648,829-39%
August 202680,471-32%
July 2026119,103+14%
June 2026104,615-14%
May 2026121,322+11%
April 2026109,528+69%
March 202664,871-9%
February 202671,495+137%
January 202630,193-29%
December 202542,469-54%

Its busiest 30 days so far ended on 2025-10-28, with 200,614 downloads.

Open meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 on Hugging Face

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