AIUnzippedAI news and analysis

Model Discovery

✨ Model FinderSynced 11/7/2026, 4:30:47 PM
📊
State of AI Models — Weekly Report
Top download gainers · rising by likes · new CPU-runnable · best by category
View report →
34,043 models
📈 Fastest-growing todayBiggest download growth since yesterday's sync
Hydrogen-1.0
by deep-principle
+30% · +6K
Language🖥️ GPUFP16
Category
AllLanguageImageAudioVideoMultimodalEmbeddingsOther
Runtime
All💻 CPU-friendly🖥️ GPU required⚡ Either
Format
AllGGUFMLXONNXAWQGPTQFP16TFLiteLlamafile
Memory
Any≤4 GB≤8 GB≤16 GB≤32 GB32 GB+
License
All🟢 Open🔒 Restricted
Source
🤗 Hugging Face🏴‍☠️ PirateFace only⚡ Both
by DAMO-NLP-SG
🖥️ GPUFP16~17 GB7B params
⬇ 131♥ 40visual-question-answering
Multimodalapache-2.0
dataset:opengvlab/videochat2-itdataset:lin-chen/sharegpt4vdataset:liuhaotian/llava-instruct-150klicense:apache-2.0
View on Hugging Face
by henilchopada
🖥️ GPUFP16
⬇ 120♥ 2visual-question-answering
Multimodalapache-2.0
multilingualdataset:huggingfacem4/a-okvqadataset:naver-clova-ix/cord-v2dataset:allenai/pixmo-docs
View on Hugging Face

Top models by task

Best models for your GPU, Mac or CPU →
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 vision-language 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