Releases MLX-VLM v0.7.4 Public — Adds support for DeepSeek V4.1 and multiple image generation enhancements
News Alibaba Releases Qwen3.8-Omni-Flash: A High-Efficiency Multimodal Model with Enhanced Audio-Visual Capabilities
News Setting Up Local LLM Development Environment on Mac Using Ollama and OpenCode with Docker Sandbox
Releases vLLM v0.29.0 Released — Model Runner V2 Now Default for All Models, New Model Support and Performance Gains
Releases llama.cpp b10730 and b10731 Released — Accelerating qwen4exp MTP Inference and Indexer Aggregation