Обсуждали свежие релизы ollama https://github.com/ollama/ollama/releases

* qwen3-vl performance improvements, including flash attention support by default
* qwen3-vl will now output less leading whitespace in the response when thinking
* Fixed issue where deepseek-v3.1 thinking could not be disabled in Ollama's new app
* Fixed issue where qwen3-vl would fail to interpret images with transparent backgrounds
* Ollama will now stop running a model before removing it via ollama rm
* Fixed issue where prompt processing would be slower on Ollama's engine
* Ignore unsupported iGPUs when doing device discovery on Windows
* Qwen3-VL: Qwen3-VL is now available in all parameter sizes ranging from 2B to 235B
* MiniMax-M2: a 230 Billion parameter model built for coding & agentic workflows available on Ollama's cloud