models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
flux1-fill-dev-fp8Qwen3.8-27B-E03-Obliterated-Omni-GGUFOrnith-1.5-9B-Omni-GGUFcudaLLM-8B-i1-GGUFcudaLLM-8B-GGUFCUDA-AutocompleteDeepSeek-OCR-GGUF-CUDAonnx-genai-example-qwen2-5-0-5b-cuda-gqa-f16stable-audio-open-1.0cudaLLM-8B-GGUFqwen3.5-9b-qwen3.6-reasoning-distilledqwen3.5-9b-qwen3.6-reasoning-distilled-GGUFPhi-3-medium-128k-instruct-onnx-cudaPhi-3-medium-4k-instruct-onnx-cudacudaLLM-8BPhi-3-vision-128k-instruct-onnx-cudaPhi-3-small-8k-instruct-onnx-cudapersonaplex-7b-v1-raw-mirrorgpt4-x-alpaca-13b-native-4bit-128g-cudaByteDance-Seed.cudaLLM-8B-GGUFVoxtral-4B-TTS-2603-ExecuTorch-CUDAgpt4-x-alpaca-13b-native-4bit-128g-cudaLFM2.5-2.6B-Windows-RTX-CUDA-GGUFllama-30b-supercot-4bit-cudagpt4-x-alpaca-13b-native-4bit-128g-cudamulti-qa-MiniLM-L6-dot-v1-2-constant-ep-MNRLtriplets-2e-5-batch32-cuda-overlappygmalion-7b-4bit-128g-cuda-2048Tokenllama-30b-supercot-4bit-128g-cudallama-30b-supercot-3bit-128g-cudadiffusiongemma-agent-iq3-cuda13