This seems extremely useful and would deserve more attention. Do you have plans to produce Qwen3.6 version? That would be great. It seems to be better than Gemma 4 26B (https://qwen.ai/blog?id=qwen3.6-35b-a3b). I'd like to try a coding version on a 32GB Mac. The full model is too large. A version for agentic use would be even better. 18B for local agent use could be a game-changer.
This seems excellent if not revolutionary, just what I've been looking for, but GPU support didn't work on my M1 and M1 Max. Is there a way to support Apple M series processors? That would be greatly appreciated. I don't have experience about this kind of programming and didn't get very far with ChatGPT.
On M1 Max, it says 14.8GB free / 32.0 GB total, but " No GPU detected" and "What Can You Run? (ZSE Ultra Mode)" only says "7B GPU + CPU Hybrid", nothing else.