448,289 public models indexed from the Hugging Face Hub, with independent VRAM estimates and license signals.
novita/kimi-k2.7-code-eagle3-mla is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
cyankiwi/Hermes-4.3-36B-AWQ-4bit is a text generation model indexed for deployment research. Estimated minimum GPU memory is 32 GB. It is publicly listed on Hugging Face.
bartowski/Vortex5_G4-Dark-Soul-26B-A4B-GGUF is a any to any model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
froggeric/Qwen3.6-27B-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.
mayocream/manga-ocr is a image to text model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
cjxzdzh/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-GPTQ-INT4 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
augustine223/Qwen3.6-35B-A3B-KO-i1-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 32 GB. It is publicly listed on Hugging Face.
mradermacher/G4-Prototype01-12B-v0.1-i1-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 12 GB. It is publicly listed on Hugging Face.
unsloth/Qwen3.5-35B-A3B 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.
bartowski/nbeerbower_Gemma4-Gutenberg-31B-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.
prathoshap/vagdhenu is a text to speech model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
mudler/Huihui3.5-67B-A3B-APEX-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 48 GB. It is publicly listed on Hugging Face.
furiosa-ai/harrier-oss-v1-0.6b is a feature extraction model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
litert-community/parakeet-tdt-0.6b-v3 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
artindnr/Strawberry is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
Trelis/tara is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
rasyosef/splade-tiny is a feature extraction model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
DavidAU/TieFighter-Holodeck-Holomax-Mythomax-F1-V1-COMPOS-20B-gguf is a text generation model indexed for deployment research. Estimated minimum GPU memory is 16 GB. It is publicly listed on Hugging Face.
akopytko/Qwen3.8-27B-NVFP4-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.
mradermacher/Mistral-NeMo-12B-Abliterated-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 12 GB. It is publicly listed on Hugging Face.
ReadyArt/For-Her-Darkside-26B-A4B-v1.4-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
AEON-7/AEON-DFlash-Qwen3.6-35B-A3B is a text generation model indexed for deployment research. Estimated minimum GPU memory is 80 GB. It is publicly listed on Hugging Face.
LocalAI-io/LocalVQE is a audio to audio model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 48 GB. It is publicly listed on Hugging Face.