Engines and Tools

Unsloth v0.1.910-beta Released with Mac MoE Support

Unsloth v0.1.910-beta brings Mac MLX MoE model memory management, REAP pruning, Flint and MOSS-Image support, and var ...

Image, Video and Audio

Hy-Nomas Video Generation Model: File List

Explore Hy-Nomas, Tencent’s world generation model enabling multi-turn interactive video generation via text pr ...

Image, Video and Audio

Ming-3.0-TTS Multilingual TTS Model: 24GB+ VRAM, ComfyUI Paths

Comfy-Org has released Ming-3.0-TTS, an open-weight text-to-speech model packaged for ComfyUI based on inclusionAI/Mi ...

New Models

Tencent Releases WeVisOne-VL Vision Language Models

Tencent’s WeChat Vision team has released WeVisOne-VL-4B and WeVisOne-VL-2B, integrating object recognition and ...

Engines and Tools

Ollama v0.40.9 Released with Apple Silicon Phonon Speech Support

Ollama v0.40.9 is released, adding Apple Silicon Phonon speech generation, d3 decision models, Flint Linux/Windows su ...

New Models

Qwen3.8-Flash-Next-E384-FP4-Local Vision-Language Model: ~96GB Memory

Explore Qwen3.8-Flash-Next-E384-FP4-Local, an unofficial NAS-optimized MoE model with reduced experts for efficient l ...

New Models

flint MoE Language Model for Coding Agents: 16GB+ VRAM, GGUF Builds

Explore Flint, a 39.8B parameter Mixture-of-Experts language model designed for coding agents, featuring tool use and ...

Engines and Tools

LocalAI v4.12.0 Released: Web UI Refresh and Streaming Audio

LocalAI v4.12.0 is released with a refreshed Web UI, streaming audio response, native decision routing, and advanced ...

New Models

Qwen3-Coder-30B-A3B-Instruct-GGUF Text Generation Model: 24GB+ VRAM

Explore the GGUF quantization of Qwen3-Coder-30B-A3B-Instruct, an efficient MoE coding model featuring agentic capabi ...

New Models

Flint-GGUF Coding MoE Language Model: 32GB+ VRAM

The GGUF version of Flint, a 39.8B parameter coding agent MoE language model, has been released by ggml-org for local ...