2,726,634 public models indexed from the Hugging Face Hub, with independent VRAM estimates and license signals.
mispeech/ced-base is a audio classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
OpenGVLab/InternVL3-2B 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.
city96/Wan2.1-T2V-14B-gguf is a text to video model indexed for deployment research. Estimated minimum GPU memory is 12 GB. It is publicly listed on Hugging Face.
FINAL-Bench/Ourbox-35B-JGOS-GGUF is a text generation model indexed for deployment research. Estimated minimum GPU memory is 32 GB. It is publicly listed on Hugging Face.
lmstudio-community/QwQ-32B-MLX-8bit is a text generation model indexed for deployment research. Estimated minimum GPU memory is 48 GB. It is publicly listed on Hugging Face.
KittenML/kitten-tts-nano-0.1 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
moonshine-ai/moonshine-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.
AtlasCloud/DeepSeek-V4-Flash-0731-FP8-DSpark is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
realrebelai/SCAIL-2_GGUF is a image to video model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Qwen/Qwen3-VL-235B-A22B-Thinking-GGUF is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 192 GB. It is publicly listed on Hugging Face.
celiudos/legal-bert-lgpd is a token classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
mudler/Qwen3.6-35B-A3B-uncensored-heretic-APEX-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 32 GB. It is publicly listed on Hugging Face.
lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-8bit is a text generation model indexed for deployment research. Estimated minimum GPU memory is 48 GB. It is publicly listed on Hugging Face.
inclusionAI/Ling-3.0-tiny is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
mlasli/Qwen3.8-27B-Heretic-Uncensored-Q5_K_M-GGUF is a text generation model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
chewwt/hpo_qwen8b_emulator is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
6block/Qwen3-32B-GGUF is a text generation model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
inference-optimization/Llama-3.2-0.5B-Instruct is a text generation model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-6bit is a text generation model indexed for deployment research. Estimated minimum GPU memory is 80 GB. It is publicly listed on Hugging Face.
JacobLinCool/MP-SENet-DNS is a audio to audio model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
timm/swinv2_base_window12to16_192to256.ms_in22k_ft_in1k is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
VesNFF/Qwen3-VL-Embedding-8B-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
namdp-ptit/ViRanker is a text classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
dbmdz/bert-base-turkish-uncased is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.