2,782,620 public models indexed from the Hugging Face Hub, with independent VRAM estimates and license signals.
OpenMed/OpenMed-ZeroShot-NER-Chemical-Medium-209M is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
numind/NuExtract-tiny is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
microsoft/TRELLIS-text-xlarge is a text to 3d model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
OpenMed/OpenMed-PII-French-BiomedBERT-Large-340M-v1 is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
PaddlePaddle/PaddleOCR-VL-1.5-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
google/canine-s is a feature extraction model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
lerobot/smolvla_libero is a robotics model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
nunchaku-ai/nunchaku-qwen-image-edit-2509 is a text to image model indexed for deployment research. Estimated minimum GPU memory is 12 GB. It is publicly listed on Hugging Face.
finegrain/finegrain-box-segmenter is a mask generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
orcarouter/GLM-5.3-Flash-MLX is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384 is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
facebook/deit-base-distilled-patch16-384 is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
timm/hrnet_w32.ms_in1k is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
OpenMed/OpenMed-PII-German-BiomedBERT-Large-340M-v1 is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
lilylilith/QIE-2511-MP-AnyLight is a image to image model indexed for deployment research. Estimated minimum GPU memory is 12 GB. It is publicly listed on Hugging Face.
timm/resnest50d.in1k is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Salesforce/blip2-itm-vit-g is a zero shot image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
timm/eva02_tiny_patch14_224.mim_in22k is a image feature extraction model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored is a text generation model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
palmfuture/Qwen3.6-27B-GPTQ-Int4 is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
facebook/wmt19-ru-en is a translation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
optimum-intel-internal-testing/tiny-random-zamba2 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
baidu/ERNIE-4.5-0.3B-PT is a text generation model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
dbmdz/bert-base-italian-uncased is a fill mask model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.