APPLE · 128GB unified memory · 6 reports
Post describes a new MLX quantization method (WinterMix) for Qwen3.5-122B-A10B, with two builds: WinterMix58 (82 GiB) and WinterMix48 (68 GiB). Benchmarks show perplexity improvements over existing MLX quants. The author is enthusiastic about the results and the method's advantages for agentic workflows on Apple Silicon.
User reports poor performance with Gemma 4 (7.5 tok/s) and Qwen3.6-27B (locking up), while Qwen3.6-35B-A3 is fast. Suspects a bug with dense models.
M5 Max 128GB · MLX · 290,000 ctx
User reports 160 tok/s prefill, 5-6 tok/s generation (later 4-5 tok/s) on M5 Max 128GB with Qwen 3.6 27B Q8 MLX at 290k context. GPU utilization 36-50%. User feels performance is lower than expected and seeks comparison.
User reports poor performance with dense models (Gemma4-31B ~7.5 t/s, Qwen3.6-27B locking up) on M5 Max 128GB, while Qwen3.6-35B-A3B MoE is fast. Mentions using DFLASH (likely flash attention).
M5 Max 128GB · MLX · 290,000 ctx
User reports 160 tok/s prefill and 5-6 tok/s generation on M5 Max 128GB with Qwen 3.6 27B Q8 MLX at 290k context. GPU utilization only 36-50%, feels off compared to expected 8-14 tok/s generation. Seeking comparison from others.
User reports poor performance with Gemma4-31B (7.5 tok/s) and Qwen3.6-27B (locking up) on M5 Max 128GB, while Qwen3.6-35B-A3 is fast. Mentions using DFLASH.