Qwen 3.5 was releases 3 days ago.
https://x.com/Alibaba_Qwen/status/2028460046510965160?s=20
The model is pretty good for Tier 2 tasks below claude or another strong model. I wanted to upload a video but it doesnt work.
Small Ollama models are:
ollama run qwen3.5:9b
ollama run qwen3.5:4b
ollama run qwen3.5:2b
ollama run qwen3.5:0.8b
They are good but not really smart. The bigger ones 397B or 122B are much better. Context window is up to 1M.
Base version is open source too ( to train own style).
Not the worst model ( its actually pretty good).
