New Models

UserRepGen-4B Text Generation Model: 4GB+ VRAM, GGUF Builds

Explore UserRepGen-4B, a 4B model by Microsoft fine-tuned from Qwen3.5-4B to generate natural language representation ...

New Models

MiniCPM-V-4.7-1B-DSpark-gguf Text Generation Model: 4GB+ VRAM

The GGUF version of MiniCPM-V-4.7-1B-DSpark, a draft model for speeding up the multimodal LLM MiniCPM-V-4.7-1B, has b ...

New Models

MiniCPM-V-4.7-35B-A3B-DSpark-gguf Draft Model for Speedup: 4GB+ VRAM

A GGUF quantized version of MiniCPM-V-4.7-35B-A3B-DSpark has been released by OpenBMB for speculative decoding accele ...

Engines and Tools

Open WebUI v0.12.1 Released: External Apps and More

Open WebUI v0.12.1 is now available, featuring external app integration in channels, Azure OpenAI Realtime support, a ...

Image, Video and Audio

drama-3-int4 Multi-Speaker TTS Model: 32GB+ VRAM, File List

An unofficial int4 quantized variant of Fish Audio’s multi-speaker speech synthesis model, drama-3-int4, has be ...

New Models

Ling-3.1-flash Hybrid Reasoning MoE Model: ~641GB Memory, GGUF Builds

inclusionAI has released Ling-3.1-flash, a 560B parameter hybrid reasoning MoE model featuring a 1M token context len ...

Image, Video and Audio

HiRO-ACEv2 Climate Simulation High-Resolution Model: File List

Learn about HiRO-ACEv2 by Allen Institute for AI, a generative model for high-resolution climate simulation downscali ...

Engines and Tools

Ollama v0.40.4 Released with Decision Models Support

Ollama v0.40.4 is out, bringing native decision models support in CLI, MLX runner enhancements, and multimodal embedd ...

Engines and Tools

Google DeepMind Announces New On-Device Scam Detection AI for…

Google DeepMind and the Singapore government announced a new AI tool to protect citizens against scams, featuring on- ...

Engines and Tools

Ollama Announces Integration with Fly.io Sprites

Ollama announced an integration with Fly.io Sprites on October 13, 2026, enabling secure AI agent execution in full L ...