The most powerful vision-language model in the Qwen model family to date.
796.4K Pulls 59 Tags Updated 1 month ago
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
1.1M Pulls 17 Tags Updated 7 months ago
386 Pulls 1 Tag Updated 8 months ago
MiniCPM-V surpasses proprietary models such as GPT-4V, Gemini Pro, Qwen-VL and Claude 3 in overall performance, and support multimodal conversation for over 30 languages.
44.9K Pulls 8 Tags Updated 1 year ago
The most powerful vision-language model in the Qwen3 model family to date.
22.7K Pulls 54 Tags Updated 1 month ago
This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). Created by https://huggingface.co/huihui-ai
7,611 Pulls 1 Tag Updated 4 months ago
2,941 Pulls 1 Tag Updated 1 year ago
888 Pulls 16 Tags Updated 1 month ago
A quantised version of the Qwen2-VL-2b model. More info available on Huggingface: https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct
512 Pulls 1 Tag Updated 9 months ago
366 Pulls 1 Tag Updated 11 months ago
132 Pulls 1 Tag Updated 10 months ago
74 Pulls 1 Tag Updated 6 months ago
61 Pulls 1 Tag Updated 6 months ago
56 Pulls 1 Tag Updated 1 month ago
38 Pulls 1 Tag Updated 1 month ago
25 Pulls 1 Tag Updated 1 month ago
20 Pulls 1 Tag Updated 1 month ago
12 Pulls 1 Tag Updated 1 month ago
11 Pulls 1 Tag Updated 1 month ago
Name: Quinn Base Model: qwen3-vl:32B (vision-enabled, multi-modal) Size: 21GB Context Length: 256K tokens Input Types: Text, Image Capabilities: Vision, Tools (experimental) Personality: Anti-waifu anee-chan. Tomboyish. Sarcast
8 Pulls 1 Tag Updated 4 weeks ago