Image, Video and Audio

higgs-audio-v3-stt-GGUF Speech-to-Text Model: 4GB+ VRAM, File List

The GGUF version of bosonai/higgs-audio-v3-stt is now available, enabling local speech recognition via llama.cpp. ...

Image, Video and Audio

Soprano-1.1-80M-GGUF Lightweight English TTS Model: File List

Explore Soprano-1.1-80M-GGUF, an open-weight 80M Text-to-Speech model in GGUF format for fast, low-latency English sp ...

Image, Video and Audio

VibeVoice-ASR-GGUF Speech Recognition and Diarization Model: 8GB+ VRAM

Microsoft’s speech recognition model VibeVoice-ASR is now available in GGUF format via ggml-org, supporting loc ...

Community

Unsloth Releases Dynamic V3.1 Quantization for Qwen3.8-27B

Unsloth releases Dynamic V3.1 quantization for Qwen3.8-27B, bringing accuracy gains and sparking discussions on Hacke ...

Image, Video and Audio

PAN2 World Model for Simulating Physical Changes: ComfyUI Paths

Comfy-Org has released the world model PAN2 repackaged for ComfyUI. Learn about its specs, hardware requirements, and ...

Image, Video and Audio

Haru-4B Speech-to-Speech Model: 12GB+ VRAM, File List

Explore Haru-4B by higurashi-ai, a low-latency, multilingual full-duplex speech-to-speech conversational base model f ...

New Models

Duo-1.0-distill-quant FP8 Quantized Realization Model: 80GB+ VRAM

Discover Duo-1.0-distill-quant, an FP8 4-step distilled Realization weight for inclusionAI’s Duo 1.0 real-time ...

Engines and Tools

llama.cpp v1.0.0 Released: Major Updates and New Features

llama.cpp v1.0.0 has been released. Read about security enhancements, FP8 KV-cache, new model support, hardware accel ...

New Models

Duo-1.2-causal-base Released for Real-time Multimodal Models

Model weights for Duo-1.2-causal-base, a full-duplex multimodal world model for real-time audio-visual interaction, a ...

New Models

Duo-1.0: Real-Time Audio-Visual Full-Duplex World Models

Learn about Duo-1.0-causal-base and Duo-1.0-distill, real-time audio-visual world models for full-duplex interaction ...