β‘ CPU/GPU
β¬ 9.5Kβ₯ 15image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ» CPUGGUF~20 GB32B params
β¬ 9.4Kβ₯ 2image-to-text
Multimodalapache-2.0
reasoningcodelicense:apache-2.0conversational
View on Hugging Faceβ‘ CPU/GPU
β¬ 9.3Kβ₯ 3image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ» CPUGGUF
β¬ 9.2Kβ₯ 0image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 9.0Kβ₯ 54visual-question-answering
Multimodalbsd-3-clause
license:bsd-3-clause
View on Hugging Faceπ» CPUGGUF~5 GB7B params
β¬ 8.7Kβ₯ 82image-to-text
Multimodalapache-2.0
dataset:prithivmlmods/caption3o-opt-v2license:apache-2.0conversational
View on Hugging Faceπ» CPUONNX
β¬ 7.7Kβ₯ 10image-to-text
Multimodal
dataset:manga109s
View on Hugging Faceπ» CPUGGUF~5 GB7B params
β¬ 7.5Kβ₯ 12image-to-text
Multimodalapache-2.0
dataset:prithivmlmods/caption3o-opt-v2license:apache-2.0conversational
View on Hugging Faceπ» CPUONNX
β¬ 7.4Kβ₯ 0image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ» CPUONNX
β¬ 7.4Kβ₯ 9image-to-text
Multimodalmit
license:mit
View on Hugging Faceπ» CPUONNX
β¬ 7.0Kβ₯ 503image-to-text
Multimodalopenrail
multilinguallicense:openrail
View on Hugging Faceπ₯οΈ GPUFP16~20 GB8B params
β¬ 6.9Kβ₯ 498image-to-text
Multimodalmit
reasoninglicense:mit
View on Hugging Faceβ‘ CPU/GPU
β¬ 6.6Kβ₯ 6image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 6.4Kβ₯ 4image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16~8 GB3B params
β¬ 6.2Kβ₯ 15image-to-text
Multimodalapache-2.0
dataset:saleh-c4/arabic-ocr-imagesdataset:aamijar/muharaf-publicdataset:johnlockejrr/rasamdataset:johnlockejrr/khatt_v1.0_dataset
View on Hugging Faceβ‘ CPU/GPU
β¬ 6.1Kβ₯ 6image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceβ‘ CPU/GPU
β¬ 6.1Kβ₯ 19image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceβ‘ CPU/GPU
β¬ 6.0Kβ₯ 4image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 5.8Kβ₯ 2image-to-text
Multimodalmit
license:mit
View on Hugging Faceβ‘ CPU/GPU
β¬ 5.7Kβ₯ 5image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceβ‘ CPU/GPU
β¬ 5.4Kβ₯ 5image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 5.1Kβ₯ 46image-to-text
Multimodalapache-2.0
dataset:x2fd/lvis-instruct4vdataset:baai/svitdataset:huggingfaceh4/ultrachat_200kdataset:mminstruction/vlfeedback
View on Hugging Faceβ‘ CPU/GPU
β¬ 4.9Kβ₯ 0image-to-text
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 4.9Kβ₯ 5image-to-text
Multimodalapache-2.0
reasoningmultilingualconversationallicense:apache-2.0
View on Hugging Face