835,060 public models indexed from the Hugging Face Hub, with independent VRAM estimates and license signals.
NbAiLab/nb-sbert-v2-base is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
ibm-granite/granite-4.0-h-350m-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
mradermacher/Artemis-31B-v1.1-heretic-i1-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
deepseek-ai/DeepSeek-V4-Pro-DSpark is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
facebook/sam-audio-base is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. Access approval is required on Hugging Face.
facebook/pe-av-small is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
BSC-LT/MrBERT-es is a fill mask model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled is a text generation model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
nyralabs/CrisperWhisper2.0_medium is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
agosh/LTX-2.5-Comfy-GGUF is a text to video model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
pszemraj/led-large-book-summary is a summarization model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
RedHatAI/phi-4-quantized.w8a8 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
furiosa-ai/Qwen3-Embedding-0.6B is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.
Mungert/Youtu-VL-4B-Instruct-GGUF is a image text to text model indexed for deployment research. Estimated minimum GPU memory is 6 GB. It is publicly listed on Hugging Face.
ZERO-POINT-AI/MARTHA-LXVII.8B_QWEN-3.5-3.6_prune_9b-3.6_base 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.
allenai/MolmoPoint-8B 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.
ManniX-ITA/Qwen3.6-27B-A3B-CoderX-MTP-GGUF is a text generation model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
GitMylo/nsfwcaption-qwen3-vl-8b-v3-gguf is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
DevQuasar/Qwen.Qwen3.8-Flash-Next-GGUF is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
mradermacher/gemma-4-31B-it-Claude-Opus-Distill-v2-i1-GGUF is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
PrunaAI/WizardLM-2-7B-GGUF-smashed is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
mradermacher/Qwen3.8-27B-Uncensored-Heretic-Abliterated-i1-GGUF is a text generation model indexed for deployment research. Estimated minimum GPU memory is 24 GB. It is publicly listed on Hugging Face.
RadixArk/Muse-Glimmer-q4km-gs128-MLX is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.
fraserprice/DeepSeek-V4-Flash-DSpark is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.