trocr-base-printedby microsoftπ₯οΈ GPUFP16β¬ 273.8Kβ₯ 234image-to-textMultimodalView on Hugging Face
trocr-large-printedby microsoftπ₯οΈ GPUFP16β¬ 168.0Kβ₯ 188image-to-textMultimodalView on Hugging Face
trocr-small-handwrittenby microsoftπ₯οΈ GPUFP16β¬ 111.7Kβ₯ 75image-to-textMultimodalView on Hugging Face
trocr-large-handwrittenby microsoftπ₯οΈ GPUFP16β¬ 39.2Kβ₯ 174image-to-textMultimodalView on Hugging Face
trocr-base-stage1by microsoftπ₯οΈ GPUFP16β¬ 19.8Kβ₯ 25image-to-textMultimodalView on Hugging Face
MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VANEWby lightx2vπ₯οΈ GPUFP16~65 GB27B paramsβ¬ 19.1Kβ₯ 65MultimodalView on Hugging Face
trocr-small-handwrittenby optimum-intel-internal-testingβ‘ CPU/GPUβ¬ 18.7Kβ₯ 0image-to-textMultimodalView on Hugging Face
trocr-small-printedby microsoftπ₯οΈ GPUFP16β¬ 15.7Kβ₯ 58image-to-textMultimodalView on Hugging Face
MiniCPM-V-2by openbmbπ₯οΈ GPUFP16β¬ 11.9Kβ₯ 507visual-question-answeringMultimodaldataset:haoyezhang/rlhf-v-datasetdataset:yirany/unimm-chatdataset:huggingfacem4/vqav2dataset:liuhaotian/llava-instruct-150kView on Hugging Face
internlm-xcomposer2-vl-7bby internlmπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 11.1Kβ₯ 84visual-question-answeringMultimodalotherlicense:otherView on Hugging Face
manga-ocr-2025-onnxby l0wgearπ» CPUONNXβ¬ 7.7Kβ₯ 10image-to-textMultimodaldataset:manga109sView on Hugging Face
LightOnOCR-2-1B-ocr-soup-GGUFby noctrexπ» CPUGGUF~1 GB1B paramsβ¬ 4.1Kβ₯ 10image-to-textMultimodalconversationalView on Hugging Face
crnn-fa-license-plate-recognition-v2by hezaraiβ‘ CPU/GPUβ¬ 3.9Kβ₯ 4image-to-textMultimodaldataset:hezarai/persian-license-plate-v1View on Hugging Face
nougat-baseby facebookπ₯οΈ GPUFP16β¬ 3.6Kβ₯ 193image-to-textMultimodalcc-by-nc-4.0license:cc-by-nc-4.0View on Hugging Face
phi4-multimodal-quantisized-ggufby ShayanCyanπ» CPUGGUFβ¬ 3.6Kβ₯ 8image-to-textMultimodalotherlicense:otherconversationalView on Hugging Face
trocr-base-handwritten-ruby kazars24π₯οΈ GPUFP16β¬ 3.5Kβ₯ 18image-to-textMultimodalView on Hugging Face
trocr-small-stage1by microsoftπ₯οΈ GPUFP16β¬ 3.5Kβ₯ 16image-to-textMultimodalView on Hugging Face
RsEvi-8B-i1-GGUFby mradermacherπ» CPUGGUF~5 GB8B paramsβ¬ 1.6Kβ₯ 0visual-question-answeringMultimodalconversationalView on Hugging Face
circuitformer-circuitvqaby MirandaAbhilashβ‘ CPU/GPUβ¬ 1.5Kβ₯ 1visual-question-answeringMultimodalView on Hugging Face
MiniCPM-V-2_6-GGUFby second-stateπ» CPUGGUFβ¬ 1.5Kβ₯ 5visual-question-answeringMultimodalconversationalView on Hugging Face
internlm-xcomposer2-4khd-7bby internlmπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 904β₯ 73visual-question-answeringMultimodalotherlicense:otherView on Hugging Face