200,823 public models indexed from the Hugging Face Hub, with independent VRAM estimates and license signals.
nvidia/Gemma-4-26B-A4B-NVFP4 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 64 GB. It is publicly listed on Hugging Face.
docling-project/docling-layout-heron is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
nvidia/Gemma-4-31B-IT-NVFP4 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 80 GB. It is publicly listed on Hugging Face.
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 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.
Harveenchadha/vakyansh-wav2vec2-tamil-tam-250 is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
openai/whisper-base is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
unsloth/Qwen3.6-35B-A3B-NVFP4 is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 80 GB. It is publicly listed on Hugging Face.
Qwen/Qwen3-14B is a text generation model indexed for deployment research. Estimated minimum GPU memory is 48 GB. It is publicly listed on Hugging Face.
Qwen/Qwen3-Coder-Next-FP8 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
timm/resnet18.a1_in1k is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
sentence-transformers/multi-qa-mpnet-base-dot-v1 is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
Qwen/Qwen2.5-0.5B is a text generation model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
airesearch/wav2vec2-large-xlsr-53-th is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Qwen/Qwen2.5-VL-32B-Instruct-AWQ is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 80 GB. It is publicly listed on Hugging Face.
cross-encoder/ms-marco-MiniLM-L12-v2 is a text ranking model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Systran/faster-whisper-base is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
openai/clip-vit-base-patch16 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.
IDEA-Research/grounding-dino-base is a zero shot object detection model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
google/gemma-3-4b-it is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 12 GB. Access approval is required on Hugging Face.
mesolitica/wav2vec2-xls-r-300m-mixed is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Lightricks/LTX-2.5 is a image to video model indexed for deployment research. Estimated minimum GPU memory is 8 GB. Access approval is required on Hugging Face.
neuralmind/bert-large-portuguese-cased is a fill mask model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Qwen/Qwen2-VL-7B-Instruct-AWQ 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.
TinyLlama/TinyLlama-1.1B-Chat-v1.0 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 6 GB. It is publicly listed on Hugging Face.