Model Gallery

0.8b 2b 35b 4b ASR CPU Cpu GPU Remote Code Enabled TTS a3b ace-step ace-step-1.5 ace-step-1.5-turbo acestep-cpp agent asr audio audio-to-text audio-transcription audio-video chat chatml chinese code command-r commercial-ok cpu deepseek default dia diffusers diffusion-large-language-model distilled edge edgetam embedding embeddings english eurollm face-embedding face-recognition face-verification falcon first-last-frame-to-video flux function-calling gemma gemma-3 gemma-4 gemma3 gemma4 german gguf glm gpu granite guf image-generation image-segmentation image-to-image image-to-text image-to-video instruction-tuned intellect jamba japanese jina kitten-tts kokoro kokoros llama2 llama3 llama3.1 llama3.2 llama3.3 llm mamba metal mistral moe moondream multilingual multimodal music music-generation nanbeige nemo nvidia object-detection ocr omni omnilingual openai openvino parakeet phi3 python quantized qwen qwen-image qwen3 qwen3-tts qwen3-tts-cpp qwen3.5 real-time reasoning reranker research-only rfdetr rnn rust rwkv salamandra sam3 sd-1.5 sd-3 sherpa-onnx smollm smollm3 smollvlm sound-generation speaker-diarization speaker-embedding speaker-verification speech-recognition speech-to-text stablediffusion streaming stt text-generation text-to-image text-to-speech text-to-text text-to-video thinking tts vad video video-generation vision vits vllm vllm-omni voice-activity-detection voice-cloning voice-recognition wan yi z-image z-image-turbo zipformer