AImodelsComparison.com 1,011 models
Menu
Models Best of Trending Can I run it? Methodology About
10 days of daily snapshots

Trending open models

Ranked by 7-day download growth from our own nightly snapshots — history Hugging Face itself doesn't show.

All tasks text-generation text-to-image ASR image-text-to-text sentence-similarity feature-extraction translation text-classification image-classification token-classification text-to-speech audio-classification image-segmentation object-detection summarization
#Model30dΔ 7dTrend
01 Qwen3.6-35B-A3B-NVFP4 unsloth · image-text-to-text 1.8 M ▲ 97.8%
02 Qwen3.5-122B-A10B Qwen · image-text-to-text 2.2 M ▲ 33.5%
03 surya-ocr-2 datalab-to · image-text-to-text 1.2 M ▲ 32.7%
04 Qwen2.5-VL-32B-Instruct Qwen · image-text-to-text 1.1 M ▲ 29.7%
05 gemma-3-27b-it-int4-awq gaunernst · image-text-to-text 1.2 M ▲ 26.6%
06 Qwen3.6-27B-NVFP4 unsloth · image-text-to-text 3.4 M ▲ 25.0%
07 SmolVLM2-500M-Video-Instruct HuggingFaceTB · image-text-to-text 1.2 M ▲ 16.7%
08 Qwen3.5-9B-AWQ QuantTrio · image-text-to-text 1.3 M ▲ 16.2%
09 Qwen3-VL-8B-Instruct-FP8 Qwen · image-text-to-text 3.2 M ▲ 14.7%
10 Qwen3.6-35B-A3B-FP8 Qwen · image-text-to-text 8.9 M ▲ 13.0%
11 Qwen3.6-27B Qwen · image-text-to-text 7.0 M ▲ 12.1%
12 moondream2 vikhyatk · image-text-to-text 2.6 M ▲ 11.7%
13 Qwen3.5-9B Qwen · image-text-to-text 12.4 M ▲ 10.6%
14 Qwen3.6-27B-AWQ-INT4 cyankiwi · image-text-to-text 2.6 M ▲ 10.3%
15 Qwen3.5-122B-A10B-FP8 Qwen · image-text-to-text 1.3 M ▲ 9.4%
16 chandra-ocr-2 datalab-to · image-text-to-text 3.2 M ▲ 8.9%
17 Qwen3.5-2B Qwen · image-text-to-text 2.6 M ▲ 8.8%
18 Qwen3.5-0.8B Qwen · image-text-to-text 3.1 M ▲ 8.3%
19 Qwen3.6-27B-FP8 Qwen · image-text-to-text 7.8 M ▲ 8.1%
20 deepseek-vl2-tiny deepseek-ai · image-text-to-text 1.3 M ▲ 7.1%
21 diffusiongemma-26B-A4B-it google · image-text-to-text 2.0 M ▲ 6.5%
22 gemma-4-31B-it-qat-w4a16-ct google · image-text-to-text 2.3 M ▲ 6.0%
23 GLM-OCR zai-org · image-text-to-text 3.8 M ▲ 5.8%
24 Qwen2.5-VL-3B-Instruct Qwen · image-text-to-text 8.2 M ▲ 5.7%
25 Qwen3.5-4B Qwen · image-text-to-text 6.7 M ▲ 5.7%
26 Qwen3-VL-2B-Instruct Qwen · image-text-to-text 2.2 M ▲ 4.3%
27 Qwen3-VL-4B-Instruct Qwen · image-text-to-text 4.0 M ▲ 4.3%
28 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive HauhauCS · image-text-to-text 1.9 M ▲ 4.1%
29 gemma-3-12b-it google · image-text-to-text 1.3 M ▲ 3.9%
30 Phi-3.5-vision-instruct microsoft · image-text-to-text 1.3 M ▲ 2.8%
31 Qwen2.5-VL-7B-Instruct Qwen · image-text-to-text 9.3 M ▲ 2.7%
32 SmolVLM-256M-Instruct HuggingFaceTB · image-text-to-text 1.1 M ▲ 2.5%
33 Llama-3.1-Nemotron-Nano-VL-8B-V1 nvidia · image-text-to-text 1.3 M ▲ 2.5%
34 InternVL2-2B OpenGVLab · image-text-to-text 1.5 M ▲ 2.4%
35 Qwen3.5-9B-GGUF unsloth · image-text-to-text 1.0 M ▲ 2.3%
36 Florence-2-base microsoft · image-text-to-text 2.8 M ▲ 2.2%
37 MiniCPM-V-4.6 openbmb · image-text-to-text 942 K ▲ 1.8%
38 Qwen3.5-27B Qwen · image-text-to-text 2.7 M ▲ 1.6%
39 Qwen3.5-4B-GGUF unsloth · image-text-to-text 1.2 M ▲ 1.6%
40 Qwen3.5-35B-A3B Qwen · image-text-to-text 2.6 M ▲ 0.4%
41 Unlimited-OCR baidu · image-text-to-text 2.7 M ▲ 0.3%
Snapshots taken nightly at 04:00 UTC from the public Hugging Face API. Also available as JSON: /api/v1/trending · methodology