New Models

ZoomGain-9B Fine-Grained Visual Language Model: 8GB+ VRAM, GGUF Builds

Discover ZoomGain-9B, a 9.4B vision-language model by inclusionAI that excels at fine-grained visual perception using ...

New Models

SingVL_S1_4B Multimodal Decision Model with Image Support: 4GB+ VRAM

Explore SingVL_S1_4B, a multimodal decision model based on Qwen3.5 that scores text, JSON, and images in a single for ...

New Models

BotPsy: 0.8B On-Device Agentic Model by Tether AI Research

Explore BotPsy, a 0.8B parameter agentic model by Tether AI Research specialized for function calling and on-device p ...

Engines and Tools

ComfyUI v0.45.0 Released with Qwen 3.x Optimizations

ComfyUI v0.45.0 is out, featuring Qwen 3.x performance improvements, new model support, and bug fixes.

Image, Video and Audio

ZONOS3-Mini 43-Language Text-to-Speech Model: File List

Explore ZONOS3-Mini, an open-source text-to-speech model by Zyphra featuring voice cloning, multi-language support, a ...

Image, Video and Audio

MiniMax-H3-Image 16-Megapixel Image Generation Model: 4GB+ VRAM

An optimized and repackaged version of the image generation model MiniMax-H3-Image has been released for ComfyUI. Not ...

Engines and Tools

NVIDIA Snapshot: Accelerate GPU Workload Cold Starts on Kubernetes

NVIDIA Snapshot is an open-source tool for Kubernetes that saves and restores GPU memory states, reducing inference c ...

New Models

WeVisOne-VL Vision-Language Model: 8GB+ VRAM

Model files for Comfy-Org/WeVisOne-VL have been released for ComfyUI, bringing object-to-pixel visual perception capa ...

Engines and Tools

Magnitude CLI v0.2.17 Released with Dynamic Context Scaling

Version 0.2.17 of the open-source inference engine Magnitude CLI is now available, featuring dynamic context length a ...

New Models

plamo-3-8b-fin-instruct Text Generation Model: 4GB+ VRAM, GGUF Builds

Preferred Networks releases PLaMo-3-8B-Fin-Instruct, a Japanese language model specialized for the financial domain o ...