MMLForge Search models, datasets, tasks… Start free

Home › Models › Image Text To Text

Best Image Text To Text Models

523

523 image text to text models on MLForge, ranked by downloads — including work from google, Qwen, cyankiwi, HauhauCS. Compare, download and run them locally on your own GPU. Free tier.

Start free Desktop app

Top Image Text To Text models

G google/gemma-4-26B-A4B-it Image Text To Text ·26.5B params 13.1M 1.2K 🤗 HF G google/gemma-4-31B-it Image Text To Text ·32.7B params 11.2M 3.1K 🤗 HF Q Qwen/Qwen3.5-9B Image Text To Text ·9.7B params 9.8M 1.6K 🤗 HF Q Qwen/Qwen3.5-4B Image Text To Text ·4.7B params 9.6M 683 🤗 HF Q Qwen/Qwen2.5-VL-7B-Instruct Image Text To Text ·8.3B params 9.4M 1.6K 🤗 HF Q Qwen/Qwen3.6-35B-A3B-FP8 Image Text To Text ·36.0B params 5.8M 284 🤗 HF Q Qwen/Qwen3-VL-8B-Instruct Image Text To Text ·8.8B params 5.8M 970 🤗 HF Q Qwen/Qwen3.6-27B Image Text To Text ·27.8B params 5.7M 1.8K 🤗 HF Q Qwen/Qwen3.6-35B-A3B Image Text To Text ·36.0B params 5.5M 2.2K 🤗 HF Q Qwen/Qwen3-VL-32B-Instruct Image Text To Text ·33.4B params 5.5M 206 🤗 HF Q Qwen/Qwen2.5-VL-3B-Instruct Image Text To Text ·3.8B params 5.4M 668 🤗 HF Q Qwen/Qwen3.6-27B-FP8 Image Text To Text ·27.8B params 5.2M 286 🤗 HF G cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit Image Text To Text ·26.6B params 4.6M 82 🤗 HF Q Qwen/Qwen3-VL-4B-Instruct Image Text To Text ·4.4B params 4.3M 400 🤗 HF Q Qwen/Qwen2-VL-2B-Instruct Image Text To Text ·2.2B params 3.8M 512 🤗 HF Q HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Image Text To Text 3.5M 2.2K 🤗 HF G zai-org/GLM-OCR Image Text To Text ·1.3B params 3.2M 1.9K 🤗 HF L llava-hf/llava-1.5-7b-hf Image Text To Text ·7.1B params 3.1M 366 🤗 HF D deepseek-ai/DeepSeek-OCR-2 Image Text To Text ·3.4B params 3.0M 1.0K 🤗 HF F microsoft/Florence-2-base Image Text To Text ·231.6M params 2.6M 381 🤗 HF Q Qwen/Qwen3.5-27B Image Text To Text ·27.8B params 2.6M 992 🤗 HF K moonshotai/Kimi-K2.6 Image Text To Text ·1058.6B params 2.5M 1.5K 🤗 HF Q Qwen/Qwen3.5-0.8B Image Text To Text ·873.4M params 2.5M 592 🤗 HF D deepseek-ai/DeepSeek-OCR Image Text To Text ·3.3B params 2.2M 3.3K 🤗 HF Q Qwen/Qwen3.5-35B-A3B Image Text To Text ·36.0B params 2.2M 1.4K 🤗 HF Q Qwen/Qwen3-VL-2B-Instruct Image Text To Text ·2.1B params 2.1M 431 🤗 HF Q Qwen/Qwen2-VL-7B-Instruct Image Text To Text ·8.3B params 2.0M 1.3K 🤗 HF Q Qwen/Qwen2-VL-7B-Instruct-AWQ Image Text To Text ·8.3B params 1.8M 49 🤗 HF C datalab-to/chandra-ocr-2 Image Text To Text ·5.3B params 1.8M 412 🤗 HF Q cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit Image Text To Text ·36.0B params 1.8M 79 🤗 HF Q Qwen/Qwen3-VL-235B-A22B-Instruct Image Text To Text ·235.7B params 1.8M 398 🤗 HF G RedHatAI/gemma-4-31B-it-FP8-block Image Text To Text ·31.3B params 1.7M 33 🤗 HF Q Lorbus/Qwen3.6-27B-int4-AutoRound Image Text To Text ·6.3B params 1.7M 115 🤗 HF Q Qwen/Qwen3.5-2B Image Text To Text ·2.3B params 1.7M 316 🤗 HF K moonshotai/Kimi-K2.5 Image Text To Text ·1058.6B params 1.7M 2.8K 🤗 HF I OpenGVLab/InternVL2-2B Image Text To Text ·2.2B params 1.7M 80 🤗 HF P microsoft/Phi-3.5-vision-instruct Image Text To Text ·4.1B params 1.6M 736 🤗 HF Q Qwen/Qwen3.5-35B-A3B-FP8 Image Text To Text ·36.0B params 1.6M 151 🤗 HF G RedHatAI/gemma-4-26B-A4B-it-FP8-Dynamic Image Text To Text ·26.6B params 1.6M 32 🤗 HF M vikhyatk/moondream2 Image Text To Text ·1.9B params 1.5M 1.4K 🤗 HF G unsloth/gemma-4-E4B-it Image Text To Text ·8.0B params 1.5M 23 🤗 HF Q Qwen/Qwen3.5-122B-A10B-FP8 Image Text To Text ·125.1B params 1.5M 107 🤗 HF G unsloth/gemma-4-26B-A4B-it-GGUF Image Text To Text 1.5M 911 🤗 HF Q Qwen/Qwen3.5-27B-FP8 Image Text To Text ·27.8B params 1.4M 135 🤗 HF Q Qwen/Qwen2.5-VL-7B-Instruct-AWQ Image Text To Text ·8.3B params 1.4M 106 🤗 HF G unsloth/gemma-4-12b-it-GGUF Image Text To Text 1.4M 704 🤗 HF Q cyankiwi/Qwen3.6-27B-AWQ-INT4 Image Text To Text ·29.3B params 1.3M 86 🤗 HF D google/diffusiongemma-26B-A4B-it Image Text To Text ·25.8B params 1.2M 1.1K 🤗 HF L nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1 Image Text To Text ·8.7B params 1.2M 181 🤗 HF Q unsloth/Qwen3.6-27B-NVFP4 Image Text To Text ·18.9B params 1.1M 96 🤗 HF G RedHatAI/gemma-4-26B-A4B-it-NVFP4 Image Text To Text ·15.1B params 1.1M 36 🤗 HF Q QuantTrio/Qwen3.6-27B-AWQ Image Text To Text ·27.8B params 1.1M 18 🤗 HF G lmstudio-community/gemma-4-26B-A4B-it-QAT-MLX-4bit Image Text To Text ·4.6B params 1.1M 1 🤗 HF Q unsloth/Qwen3.5-9B-GGUF Image Text To Text 1.1M 725 🤗 HF Q lmstudio-community/Qwen3.6-27B-MLX-4bit Image Text To Text ·4.7B params 1.0M 7 🤗 HF Q lmstudio-community/Qwen3.6-27B-MLX-8bit Image Text To Text ·8.0B params 1.0M 5 🤗 HF G cyankiwi/gemma-4-31B-it-AWQ-4bit Image Text To Text ·33.1B params 1.0M 50 🤗 HF Q unsloth/Qwen3.5-4B-GGUF Image Text To Text 998.9K 297 🤗 HF S HuggingFaceTB/SmolVLM-256M-Instruct Image Text To Text ·256.5M params 979.4K 372 🤗 HF Q lmstudio-community/Qwen3.6-27B-MLX-6bit Image Text To Text ·6.3B params 964.1K 2 🤗 HF Q lmstudio-community/Qwen3.6-27B-MLX-5bit Image Text To Text ·5.5B params 960.6K 🤗 HF L llava-hf/llava-onevision-qwen2-0.5b-ov-hf Image Text To Text ·893.7M params 952.6K 55 🤗 HF D deepseek-ai/deepseek-vl2-tiny Image Text To Text ·3.4B params 910.7K 248 🤗 HF G google/gemma-4-31B-it-qat-w4a16-ct Image Text To Text ·33.6B params 905.9K 33 🤗 HF L nvidia/LocateAnything-3B Image Text To Text ·3.8B params 896.1K 2.5K 🤗 HF U baidu/Unlimited-OCR Image Text To Text ·3.3B params 885.0K 1.7K 🤗 HF Q Qwen/Qwen3.5-35B-A3B-GPTQ-Int4 Image Text To Text ·36.0B params 883.0K 90 🤗 HF Q unsloth/Qwen3.6-35B-A3B-GGUF Image Text To Text 877.6K 1.3K 🤗 HF Q unsloth/Qwen3.6-27B-MTP-GGUF Image Text To Text 868.5K 885 🤗 HF Q unsloth/Qwen3-VL-2B-Instruct-GGUF Image Text To Text 851.2K 34 🤗 HF K moonshotai/Kimi-K2.7-Code Image Text To Text ·1058.6B params 844.4K 1.0K 🤗 HF M openbmb/MiniCPM-V-4.6 Image Text To Text ·1.3B params 835.2K 1.1K 🤗 HF Q Qwen/Qwen3.5-397B-A17B-FP8 Image Text To Text ·403.4B params 831.7K 181 🤗 HF G unsloth/gemma-4-26B-A4B-it-qat-GGUF Image Text To Text 819.3K 231 🤗 HF Q cyankiwi/Qwen3.5-9B-AWQ-4bit Image Text To Text ·9.9B params 795.8K 33 🤗 HF Q unsloth/Qwen3.6-35B-A3B-MTP-GGUF Image Text To Text 777.7K 604 🤗 HF Q AxionML/Qwen3.5-9B-NVFP4 Image Text To Text ·6.6B params 773.4K 18 🤗 HF Q Qwen/Qwen3.5-122B-A10B Image Text To Text ·125.1B params 772.4K 580 🤗 HF L LiquidAI/LFM2.5-VL-450M Image Text To Text ·448.7M params 770.4K 191 🤗 HF Q lmstudio-community/Qwen3.5-9B-MLX-4bit Image Text To Text ·1.9B params 764.1K 4 🤗 HF L llava-hf/llava-v1.6-mistral-7b-hf Image Text To Text ·7.6B params 737.2K 311 🤗 HF T trl-internal-testing/tiny-Qwen2_5_VLForConditionalGeneration Image Text To Text ·3.9M params 733.3K 🤗 HF G google/gemma-4-26B-A4B Image Text To Text ·26.5B params 690.8K 331 🤗 HF Q Qwen/Qwen3-VL-8B-Instruct-FP8 Image Text To Text ·8.8B params 687.8K 73 🤗 HF G unsloth/gemma-4-E4B-it-GGUF Image Text To Text 687.4K 523 🤗 HF B Salesforce/blip2-opt-2.7b Image Text To Text ·3.7B params 685.4K 445 🤗 HF G unsloth/gemma-4-E2B-it-GGUF Image Text To Text 680.7K 250 🤗 HF Q lmstudio-community/Qwen3.5-9B-MLX-8bit Image Text To Text ·3.0B params 679.5K 1 🤗 HF Q QuantTrio/Qwen3.6-35B-A3B-AWQ Image Text To Text ·36.0B params 678.0K 26 🤗 HF M MiniMaxAI/MiniMax-M3-MXFP8 Image Text To Text ·440.3B params 673.9K 43 🤗 HF S HuggingFaceTB/SmolVLM2-500M-Video-Instruct Image Text To Text ·507.5M params 670.7K 155 🤗 HF F microsoft/Florence-2-large Image Text To Text ·776.7M params 665.6K 1.8K 🤗 HF Q lmstudio-community/Qwen3.6-35B-A3B-MLX-4bit Image Text To Text ·5.9B params 664.8K 2 🤗 HF Q lmstudio-community/Qwen3.6-35B-A3B-MLX-8bit Image Text To Text ·10.2B params 646.6K 🤗 HF M allenai/Molmo2-8B Image Text To Text ·8.7B params 637.6K 189 🤗 HF Q lmstudio-community/Qwen3.6-35B-A3B-MLX-6bit Image Text To Text ·8.0B params 634.3K 2 🤗 HF O allenai/olmOCR-2-7B-1025-FP8 Image Text To Text ·8.3B params 629.2K 243 🤗 HF G google/gemma-4-31B Image Text To Text ·32.7B params 624.0K 444 🤗 HF G unsloth/gemma-4-31B-it-GGUF Image Text To Text 622.3K 509 🤗 HF I OpenGVLab/InternVL2-1B Image Text To Text ·938.2M params 614.2K 82 🤗 HF N nvidia/NVIDIA-Nemotron-Parse-v1.1 Image Text To Text ·956.8M params 611.3K 171 🤗 HF Q unsloth/Qwen3.6-27B-GGUF Image Text To Text 592.3K 842 🤗 HF G zai-org/GLM-4.1V-9B-Thinking Image Text To Text ·10.3B params 585.4K 777 🤗 HF D rednote-hilab/dots.mocr Image Text To Text ·3.0B params 579.1K 139 🤗 HF Q cyankiwi/Qwen3.5-27B-AWQ-4bit Image Text To Text ·28.6B params 562.3K 40 🤗 HF Q cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4 Image Text To Text ·29.0B params 553.6K 40 🤗 HF Q Qwen/Qwen3-VL-30B-A3B-Instruct Image Text To Text ·31.1B params 548.8K 582 🤗 HF G HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive Image Text To Text 542.2K 866 🤗 HF Q groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit Image Text To Text ·27.4B params 537.7K 37 🤗 HF G unsloth/gemma-4-31B-it-unsloth-bnb-4bit Image Text To Text ·31.3B params 533.6K 20 🤗 HF Q DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF Image Text To Text 527.4K 505 🤗 HF G RedHatAI/gemma-3-27b-it-FP8-dynamic Image Text To Text ·27.4B params 522.0K 13 🤗 HF Q QuantTrio/Qwen3.5-9B-AWQ Image Text To Text ·9.7B params 489.5K 22 🤗 HF N nanonets/Nanonets-OCR2-3B Image Text To Text ·3.8B params 475.1K 509 🤗 HF G QuantTrio/gemma-4-31B-it-AWQ Image Text To Text ·31.3B params 473.9K 12 🤗 HF Q HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive Image Text To Text 473.5K 482 🤗 HF Q Qwen/Qwen3-VL-4B-Instruct-FP8 Image Text To Text ·4.8B params 466.4K 63 🤗 HF Q cyankiwi/Qwen3.5-2B-AWQ-4bit Image Text To Text ·2.3B params 464.8K 3 🤗 HF Q palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4 Image Text To Text ·36.0B params 451.6K 25 🤗 HF Q Qwen/Qwen3.5-397B-A17B Image Text To Text ·403.4B params 446.8K 1.5K 🤗 HF

Showing the top 120 of 523 by downloads. Browse all in MLForge →

Other tasks