2,417,302 public models indexed from the Hugging Face Hub, with independent VRAM estimates and license signals.
Qwen/Qwen3.5-27B-FP8 is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 64 GB. It is publicly listed on Hugging Face.
lmstudio-community/gemma-4-E2B-it-MLX-5bit is a any to any model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
timm/tf_mobilenetv3_large_minimal_100.in1k is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Qwen/Qwen3-30B-A3B-FP8 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 80 GB. It is publicly listed on Hugging Face.
HuggingFaceTB/SmolLM2-1.7B-Instruct is a text generation model indexed for deployment research. Estimated minimum GPU memory is 6 GB. It is publicly listed on Hugging Face.
OpenMOSS-Team/MOSS-Audio-Tokenizer is a feature extraction model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
moonshotai/Kimi-VL-A3B-Instruct 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.
handy-computer/Qwen3-ASR-1.7B-gguf is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
amd/DeepSeek-R1-MXFP4 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
timm/convnext_small.fb_in22k_ft_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.
nomic-ai/CodeRankEmbed is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
AlfonsoM/Rocinante-12B-v1.1-GPTQ is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 32 GB. It is publicly listed on Hugging Face.
mistralai/Voxtral-Mini-3B-2507 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 12 GB. It is publicly listed on Hugging Face.
lmstudio-community/gemma-4-26B-A4B-it-QAT-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
Qwen/Qwen3-VL-32B-Instruct-FP8 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.
OpenMed/OpenMed-NER-PathologyDetect-TinyMed-135M is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
OpenMed/OpenMed-NER-OncologyDetect-BigMed-278M is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
urchade/gliner_large-v2 is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
sentence-transformers/msmarco-MiniLM-L6-v3 is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
OpenMed/OpenMed-NER-ChemicalDetect-ModernMed-395M is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
mistralai/Mistral-Small-3.2-24B-Instruct-2506 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 64 GB. It is publicly listed on Hugging Face.
ggml-org/gpt-oss-120b-GGUF is a text generation model indexed for deployment research. Estimated minimum GPU memory is 80 GB. It is publicly listed on Hugging Face.
sumedh/wav2vec2-large-xlsr-marathi is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Comfy-Org/Mage-Flow is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.