Qwen/Qwen3-VL-4B-Thinking-FP8 download history
Qwen/Qwen3-VL-4B-Thinking-FP8 is a 4.8B-parameter image text to text model by Qwen. In the last 30 days it was downloaded 792 times (226 in the last 7 days), and 93,932 times in total.
It ranks #43,467 on the Hub by monthly downloads and #3,962 among image text to text models.
It has 41 likes.
It is a quantization of Qwen/Qwen3-VL-4B-Thinking.
1 models build on Qwen3-VL-4B-Thinking-FP8: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 1,074 times in the last 30 days. See the Qwen3-VL-4B-Thinking-FP8 galaxy.
Most downloaded derivatives
- unsloth/Qwen3-VL-4B-Thinking-FP8 (quantized), 282 downloads in 30 days
Open Qwen/Qwen3-VL-4B-Thinking-FP8 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.