Ollama Adds Kimi-K2.5, gpt-oss, and MiniMax Models — Local LLM Gateway Hits 169,758 Stars

GitHub·medium signal

Ollama continues to expand its local model support, now listing Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, and Gemma among its runnable models. The addition of gpt-oss (OpenAI's open-source model family) and Moonshot's Kimi-K2.5 represent significant new entries for local inference. At nearly 170K stars, Ollama remains the dominant local LLM runtime and continues to be the first place new open models get integrated.