Vision language models
Models that connect image and text inputs for tasks such as visual question answering or image-text generation
Where it stands
Open models1374 products0.94× its peers
Fastest products
1OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF · Open models336×
2nvidia/Qwen2.5-VL-7B-Instruct-NVFP4 · Open models208×3omlab/VLX-Seek-1.5-10B · Open models160×
4byteshape/Qwen3.8-27B-GGUF · Open models84×5mlx-community/gemma-3-12b-it-4bit · Open models78×
6zhiqiulin/clip-flant5-xl · Open models69×
7swiss-ai/Apertus-v1.5-8B · Open models63×8neroued/Qwen3.6-27B-NInfer · Open models63×
9stepfun-ai/Step-3.7-Flash-NVFP4 · Open models58×10deepseek-ai/DeepSeek-V4-Flash-Vision-Exp · Open models53×11ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF · Open models30×
12pyros-vault/Qwen3.8-27B-Uncensored-NInfer · Open models29×
13cesarsal1nas/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-Q4_K_M-GGUF · Open models28×
14datalab-to/chandra · Open models27×15QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 · Open models26×
16huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated · Open models25×
17ibm-granite/granite-4.0-3b-vision · Open models23×
18neroued/Qwen3.6-35B-A3B-NInfer · Open models21×
19unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF · Open models20×20Alibaba-DAMO-Academy/RynnBrain-2B · Open models19×21coder3101/Qwen3.5-27B-heretic · Open models19×
22google/gemma-4-31B-it-qat-q4_0-unquantized · Open models17×
23neroued/Qwen3.8-27B-NInfer · Open models16×
24mudler/Ornith-1.5-35B-A3B-APEX-GGUF · Open models16×
25tiny-random/qwen3.5-moe · Open models16×
2,056 products carry this theme. “× its peers” is the theme's median growth against the place's median.