Compatibility check
Can I run Qwen3.6 35B A3B on Apple M5 Max (40-core GPU)?
Yes — it runs.best quant: Q4_K_M
Decode speed
201 tok/sest
Usable context
262K
Memory
128 GB
Q4_K_MFits in memory201 tok/sest · 262K ctx
Q5_K_MFits in memory171 tok/sest · 262K ctx
Q8_0Fits in memory115 tok/sest · 262K ctx