Image Text to Text Models
Vision-language models that accept combined image and text input and generate text output.
- Top-10 combined DL 30D
- 77.1M
- Tasks directory position
- See all tasks
- Growth history
- Available
- Last refresh
- Sep 22, 2026
Trending now
| # | Model | Task | DL 30D | 7D | Likes | Params |
|---|---|---|---|---|---|---|
| 1 | JEV-27B-VLautotrust | Image Text to Text | 1.5M | — | ||
| 2 | clefCloudflare | Image Text to Text | 9,513 | — | ||
| 3 | clef-flashCloudflare | Image Text to Text | 15.7K | — | ||
| 4 | TeleOCRStarDoc-AI | Image Text to Text | 27.8K | 79.6%(up) | ||
| 5 | Qwen3.8-27BQwen | Image Text to Text | 6.8M | 19.2%(up) | ||
| 6 | Qwen3.8-Flash-Next-GSQ-RCO-GGUFISTA-DASLab | Image Text to Text | 3.1M | — | ||
| 7 | ZDTaichu5.0-9BTaichuAI | Image Text to Text | 13K | — | ||
| 8 | Qwen3.8-Flash-NextQwen | Image Text to Text | 1.6M | 20.0%(up) | ||
| 9 | DeepSeek-V4.1-Flashdeepseek-ai | Image Text to Text | 1.3M | 77.6%(up) | ||
| 10 | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUFDavidAU | Image Text to Text | 2.1M | 54.0%(up) |
Most downloaded
| Model | Task | DL 30D | 7D | Likes | Params |
|---|---|---|---|---|---|
| gemma-4-26B-A4B-itgoogle | Image Text to Text | 12.5M | 5.0%(up) | ||
| Qwen3-VL-8B-InstructQwen | Image Text to Text | 10.4M | 6.6%(up) | ||
| gemma-4-31B-itgoogle | Image Text to Text | 9.6M | 4.0%(up) | ||
| Qwen3.5-9BQwen | Image Text to Text | 8.7M | 4.6%(up) | ||
| Qwen3.5-4BQwen | Image Text to Text | 8M | 3.5%(up) | ||
| Qwen3.8-27BQwen | Image Text to Text | 6.8M | 19.2%(up) | ||
| GLM-5.3-Flashzai-org | Image Text to Text | 6.2M | 87.0%(up) | ||
| Qwen2.5-VL-7B-InstructQwen | Image Text to Text | 5.5M | 1.5%(up) | ||
| Qwen3.8-27B-FP8Qwen | Image Text to Text | 4.8M | 14.7%(up) | ||
| Qwen3.6-35B-A3B-FP8Qwen | Image Text to Text | 4.7M | 3.1%(up) |
Fastest growing
Downloads gained over the last seven tracked days.
| Model | Task | DL 30D | 7D7D gained | Likes | Params |
|---|---|---|---|---|---|
| Qwen3-VL-8B-InstructQwen | Image Text to Text | 10.4M | +4.3M | ||
| gemma-4-26B-A4B-itgoogle | Image Text to Text | 12.5M | +2.9M | ||
| Qwen3.5-9BQwen | Image Text to Text | 8.7M | +2.8M | ||
| gemma-4-31B-itgoogle | Image Text to Text | 9.6M | +2.3M | ||
| Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUFcdiamond | Image Text to Text | 3.8M | +1.8M | ||
| Qwen3.5-4BQwen | Image Text to Text | 8M | +1.6M | ||
| GLM-5.3-Flashzai-org | Image Text to Text | 6.2M | +1.5M | ||
| Qwen3.8-27BQwen | Image Text to Text | 6.8M | +1.5M | ||
| Qwen2.5-VL-7B-InstructQwen | Image Text to Text | 5.5M | +1.5M | ||
| Qwen3.5-2BQwen | Image Text to Text | 4.3M | +1.3M |
New & notable
Published within the last 90 days with meaningful traction.
| Model | Task | DL 30D | 7D7D gained | Likes | Params | Published |
|---|---|---|---|---|---|---|
| Qwen3.8-27BQwen | Image Text to Text | 6.8M | +1.5M | Aug 5, 2026 | ||
| GLM-5.3-Flashzai-org | Image Text to Text | 6.2M | +1.5M | Aug 25, 2026 | ||
| Qwen3.8-27B-FP8Qwen | Image Text to Text | 4.8M | +1.2M | Aug 13, 2026 | ||
| Qwen3.8-27B-MLX-4bitlmstudio-community | Image Text to Text | 4.2M | +1.1M | Aug 14, 2026 | ||
| Qwen3.8-27B-MLX-8bitlmstudio-community | Image Text to Text | 4M | +1M | Aug 14, 2026 | ||
| Qwen3.8-27B-MLX-6bitlmstudio-community | Image Text to Text | 4M | +1M | Aug 14, 2026 | ||
| Qwen3.8-27B-MLX-5bitlmstudio-community | Image Text to Text | 4M | +1M | Aug 14, 2026 | ||
| Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUFcdiamond | Image Text to Text | 3.8M | +1.8M | Aug 17, 2026 | ||
| Qwen3.8-Flash-Next-GSQ-RCO-GGUFISTA-DASLab | Image Text to Text | 3.1M | +53.1K | Sep 7, 2026 | ||
| Huihui-Qwen3.8-27B-abliterated-GGUFhuihui-ai | Image Text to Text | 2.1M | +550.2K | Aug 16, 2026 |