Top open vision-language models
Models that process both images and text to generate text responses.
How this list works: ranked by Hugging Face downloads in the last 30 days, among models with 1,000+ downloads.
| # | Model | Author | Downloads (30 days) | Likes | Size | License | Commercial use | Runs on |
|---|---|---|---|---|---|---|---|---|
| 1 | gemma-4-26B-A4B-it | 10.5M | 1.7K | 26B | Apache 2.0 | Yes | GPU | |
| 2 | gemma-4-31B-it | 9M | 4.2K | 31B | Apache 2.0 | Yes | GPU | |
| 3 | Qwen3.5-4B | Qwen | 7.9M | 1.1K | 4B | Apache 2.0 | Yes | GPU |
| 4 | Qwen3.5-9B | Qwen | 7.8M | 2.2K | 9B | Apache 2.0 | Yes | GPU |
| 5 | Qwen3.8-27B | Qwen | 7.5M | 18K | 27B | Apache 2.0 | Yes | GPU |
| 6 | GLM-5.3-Flash | zai-org | 6.5M | 2.9K | – | MIT | Yes | GPU |
| 7 | Qwen3-VL-8B-Instruct | Qwen | 6M | 1.2K | 8B | Apache 2.0 | Yes | GPU |
| 8 | Qwen3.8-Flash-Next-GSQ-RCO-GGUF | ISTA-DASLab | 5.9M | 945 | – | Apache 2.0 | Yes | CPU |
| 9 | Qwen2.5-VL-7B-Instruct | Qwen | 5.2M | 1.7K | 7B | Apache 2.0 | Yes | GPU |
| 10 | Qwen3.8-27B-FP8 | Qwen | 4.4M | 928 | 27B | Apache 2.0 | Yes | GPU |
| 11 | Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF | cdiamond | 4.3M | 25 | 27B | Apache 2.0 | Yes | CPU |
| 12 | Qwen3.6-27B-FP8 | Qwen | 4.1M | 358 | 27B | Apache 2.0 | Yes | GPU |
| 13 | Qwen3.8-27B-MLX-4bit | lmstudio-community | 4.1M | 100 | 27B | Apache 2.0 | Yes | CPU |
| 14 | Qwen3.5-2B | Qwen | 4M | 429 | 2B | Apache 2.0 | Yes | GPU |
| 15 | Qwen3.6-35B-A3B-FP8 | Qwen | 4M | 434 | 35B | Apache 2.0 | Yes | GPU |
| 16 | Qwen3.8-27B-MLX-5bit | lmstudio-community | 3.9M | 6 | 27B | Apache 2.0 | Yes | CPU |
| 17 | Qwen3.8-27B-MLX-6bit | lmstudio-community | 3.9M | 34 | 27B | Apache 2.0 | Yes | CPU |
| 18 | Qwen3.8-27B-MLX-8bit | lmstudio-community | 3.9M | 43 | 27B | Apache 2.0 | Yes | CPU |
| 19 | Qwen3.6-35B-A3B | Qwen | 3.7M | 3K | 35B | Apache 2.0 | Yes | GPU |
| 20 | Qwen3.8-Flash-Next | Qwen | 2.5M | 6.3K | – | Custom (other) | Check the license | GPU |
| 21 | Huihui-Qwen3.8-27B-abliterated-GGUF | huihui-ai | 2.4M | 1.4K | 27B | Apache 2.0 | Yes | CPU |
| 22 | Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF | HauhauCS | 2.4M | 1.9K | 27B | Apache 2.0 | Yes | CPU |
| 23 | Qwen3.6-27B | Qwen | 2.3M | 2.3K | 27B | Apache 2.0 | Yes | GPU |
| 24 | DeepSeek-OCR | deepseek-ai | 2.1M | 3.4K | – | MIT | Yes | GPU |
| 25 | Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF | DavidAU | 1.9M | 1.1K | 9B | Apache 2.0 | Yes | CPU |
Other model comparisons
Top open language modelsTop open image modelsTop open audio modelsTop open video modelsTop open embedding modelsTop open multimodal modelsTop open text-generation models (LLMs)Top open text-to-image modelsTop open text-to-speech modelsTop open speech-recognition modelsTop open feature-extraction modelsTop open sentence-similarity modelsTop open image-to-text modelsTop open image-classification modelsTop open image-segmentation modelsTop open object-detection modelsTop open depth-estimation modelsTop open audio-classification modelsTop open video-classification models