Engines and Tools

ggml v1.0.0 Released: Major Version Update and Improvements

ggml v1.0.0 has been released. This major update brings API cleanups, RPC protocol updates, scheduler optimizations, ...

Image, Video and Audio

TTS-V1 Chinese Text-to-Speech Model: File List

An overview of autotrust/TTS-V1, an open-weight Chinese TTS model featuring four voice presets and integrated normali ...

New Models

SingVL_S1_4B_GGUF 4B Multimodal Decision-Making Model: 4GB+ VRAM

Explore inclusionAI’s Sing VL S1 4B GGUF, a 4B multimodal decision model based on Qwen3.5 supporting text, JSON ...

Image, Video and Audio

PrunaAI Releases Object Removal LoRA for Qwen-Image-2.1

PrunaAI has released LoRA adapters for Qwen-Image-2.1 specifically designed for object removal, including ComfyUI wor ...

Engines and Tools

Diffusers 0.43.0 Released with 5 New Modular Pipelines

Diffusers 0.43.0 is out with 5 new modular pipelines (MiniMax-H3-Image, Pika H3 Flex, P-H3-Image, Kandinsky S2V 1.0, ...

New Models

Qwen3.5-4B-GGUF Vision-Language Model: 4GB+ VRAM

Explore ggml-org/Qwen3.5-4B-GGUF, a GGUF quantized multimodal 4B language model supporting text, image, and video inp ...

Engines and Tools

Unsloth v0.1.917-beta Released with Major Performance Boosts

Unsloth v0.1.917-beta is out, bringing UI improvements, VRAM reductions for FLUX, faster training on T4 GPUs, and new ...

Engines and Tools

Yogurt: Local Open-Source Alternative to Granola

Meet Yogurt, a free, private, open-source desktop app for meeting transcription, summarization, and Q&A running ...

New Models

ZoomGain-9B-GGUF Vision-Language Model: 8GB+ VRAM

inclusionAI has released ZoomGain-9B-GGUF, converting the ZoomGain-9B vision-language model into the GGUF format for ...

New Models

ZoomGain-4B: 4GB+ VRAM, GGUF Builds

Discover ZoomGain-4B, a vision-language model specialized in fine-grained visual recognition, featuring specs, perfor ...