local-inference-lab/Qwen3.8-Flash-Next-NVFP4 download history

local-inference-lab/Qwen3.8-Flash-Next-NVFP4 is a 92.7B-parameter image text to text model by local-inference-lab. In the last 30 days it was downloaded 100,100 times (8,089 in the last 7 days), and 191,838 times in total.

It ranks #2,322 on the Hub by monthly downloads and #340 among image text to text models.

It has 63 likes.

It is a quantization of Qwen/Qwen3.8-Flash-Next.

11 models build on Qwen3.8-Flash-Next-NVFP4: 5 quantized, 5 fine-tuned, 0 adapters and 1 merges. Together with the original they were downloaded 103,204 times in the last 30 days. See the Qwen3.8-Flash-Next-NVFP4 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 2026-11-18100,100-23%
October 2026129,331+268%

Its busiest 30 days so far ended on 2026-10-31, with 129,331 downloads.

Open local-inference-lab/Qwen3.8-Flash-Next-NVFP4 on Hugging Face

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