The Q4_K_S quantized GGUF version of the Qwen3-Omni-30B-A3B-Thinking model, supporting multimodal processing of text, vision, and audio, and achieving efficient reasoning through llama.cpp. This version significantly reduces the file size and improves the reasoning speed while ensuring quality.

MultimodalGgufMultiple Languages

AKI is a multimodal foundation model that achieves cross-modal mutual attention (MMA) by unlocking the causal attention mechanism in LLMs, addressing vision-language misalignment without additional parameters or training time.

MultimodalSafetensorsEnglish

Japanese speech-to-text model based on whisper-large-v3-turbo architecture, supporting katakana output with pitch accent annotation

Audio ProcessingTransformersJapanese

A Japanese natural language inference cross-encoder trained on tohoku-nlp/bert-base-japanese-v3, supporting entailment, neutral, and contradiction judgments

Natural Language ProcessingSafetensorsMultiple Languages

A Japanese natural language inference model based on BERT architecture, trained on the JSNLI dataset, used to determine logical relationships (entailment/neutral/contradiction) between sentence pairs

Natural Language ProcessingSafetensorsMultiple Languages

A DistilBERT-based SMS spam classification model, fine-tuned on the sms_spam dataset, used to identify spam messages.

Natural Language ProcessingTransformersEnglish

A Stable Diffusion model trained with Dreambooth, specifically designed for generating 'Marco'-style female images.

Computer VisionDiffusers