Qwen3.5 122B (10B active)

User reports a new MLX quantization method, WinterMix, for Qwen3.5-122B-A10B, with two builds: WinterMix58 at 82 GiB and WinterMix48 at 68 GiB. Benchmarks show perplexity improvements over existing MLX quants. The user is enthusiastic about the results and the method's advantages for agentic workflows on Apple Silicon.