#local-ai
- Ollama v0.23.1: Gemma 4 MTP Speculative Decoding Delivers 2× Speed on Apple Silicon tools
- llama.cpp b9085: MiMo-V2.5 Flash Attention and Vertex AI Server Support tools
- llama.cpp Adds gpt-oss-20b Support in May 12 Build tools
- Ollama v0.23.3: MLX Runner Fixes and macOS 26 Metal Compatibility Ollama tools